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

    Neuronpedia

    INDEX
    Explanations

    phrases related to understanding and awareness

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

    know why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DebuggerNonUser
    -0.45
     tentang
    -0.42
    concer
    -0.41
    igurumi
    -0.41
    wohl
    -0.40
    enciaga
    -0.39
     previous
    -0.39
     Concerning
    -0.38
     terdekat
    -0.38
    Fury
    -0.37
    POSITIVE LOGITS
    GEBURTSDATUM
    0.52
    RTSC
    0.49
     ब्रेकडाउन
    0.49
    #+#
    0.48
    :
    0.47
     '{@
    0.46
     незавершена
    0.45
    这不是
    0.43
     there
    0.43
     why
    0.41
    Act Density 0.044%

    No Known Activations