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

    Neuronpedia

    INDEX
    Explanations

    boolean logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dire
    -0.07
    Arm
    -0.06
     Bare
    -0.06
     bowling
    -0.06
    �
    -0.06
     WWW
    -0.06
    _ck
    -0.06
     autofocus
    -0.06
     Flash
    -0.06
    ํ
    -0.06
    POSITIVE LOGITS
    Vi
    0.07
    istrovství
    0.07
    Japan
    0.07
     vocational
    0.07
    codegen
    0.07
    rcode
    0.07
    otional
    0.07
    ерь
    0.06
    <Integer
    0.06
    739
    0.06
    Act Density 0.000%

    No Known Activations