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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific symbolic or representational sequences within the text

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

    URL structure or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zgod
    -0.35
     Corea
    -0.35
     convinced
    -0.35
     about
    -0.34
    valg
    -0.33
    Credito
    -0.33
    sehen
    -0.33
     convain
    -0.32
     Lage
    -0.32
     Hafen
    -0.32
    POSITIVE LOGITS
    rungsseite
    0.77
    ThroughAttribute
    0.76
    WireFormatLite
    0.67
    linawan
    0.66
    URLException
    0.63
     surla
    0.63
    KommentareTeilen
    0.62
    IUrlHelper
    0.62
    oneofs
    0.61
     Infórmanos
    0.60
    Act Density 1.185%

    No Known Activations