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

    Neuronpedia

    INDEX
    Explanations

    programming/lists/generic content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الاطلاع
    -0.66
     the
    -0.58
    +#+#
    -0.57
    لينكات
    -0.57
    fjspx
    -0.55
    openSession
    -0.54
    SourceChecksum
    -0.54
    MessageOf
    -0.52
     rates
    -0.52
     innovation
    -0.51
    POSITIVE LOGITS
     wild
    0.63
    wild
    0.63
     itſelf
    0.60
     spontaneously
    0.60
     naturally
    0.59
    WILD
    0.57
     spontan
    0.56
     spont
    0.56
     natu
    0.56
     willy
    0.53
    Act Density 0.000%

    No Known Activations