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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tro
    -0.07
     teaches
    -0.06
    ?',
    -0.06
    lv
    -0.06
     weapons
    -0.06
    ottes
    -0.06
    ENCIL
    -0.06
    _DEL
    -0.06
    strings
    -0.06
    -lat
    -0.06
    POSITIVE LOGITS
     archival
    0.07
    _mult
    0.07
    �
    0.07
     CPPUNIT
    0.07
    .getInput
    0.06
    _INTERNAL
    0.06
    .Prop
    0.06
     onCreateView
    0.06
    แส
    0.06
     الرح
    0.06
    Act Density 0.205%

    No Known Activations