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

    Neuronpedia

    INDEX
    Explanations

    click

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bc
    -0.07
     precondition
    -0.07
     Payne
    -0.06
    _messages
    -0.06
     Ach
    -0.06
    .mit
    -0.06
    .instructions
    -0.06
    �
    -0.06
    erialized
    -0.06
     fus
    -0.06
    POSITIVE LOGITS
    場合
    0.07
    แหล
    0.06
    "type
    0.06
    /apache
    0.06
    -basket
    0.06
     заходів
    0.06
     ############################################################################
    0.06
     ErrorMessage
    0.06
     gchar
    0.06
    .Admin
    0.06
    Act Density 0.051%

    No Known Activations