Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of various forms of the verb "to hear" and "to read"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "read somewhere" or "heard somewhere."

    np_acts-logits-general · gemini-2.0-flash

    read that somewhere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Permalink
    -0.56
    brainly
    -0.55
    ėjimas
    -0.53
    bleib
    -0.53
    éda
    -0.52
    IsContent
    -0.52
    ứ
    -0.52
    ėd
    -0.52
     Dory
    -0.52
    AutoModerator
    -0.51
    POSITIVE LOGITS
     فريبيس
    0.65
    complexContent
    0.63
    rungsseite
    0.55
     "..\..\..\
    0.55
    MethodManager
    0.54
    Autoritní
    0.53
     Signalez
    0.51
    ритори
    0.50
     ligiloj
    0.48
    听说
    0.47
    Act Density 0.193%

    No Known Activations