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

    Neuronpedia

    INDEX
    Explanations

    EU policies and discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ---------------------------------------------------------------------------↵
    -0.06
     commented
    -0.06
    ?id
    -0.06
     Zuckerberg
    -0.06
     conditioned
    -0.06
     Claude
    -0.06
     σκο
    -0.06
    ué
    -0.06
     repar
    -0.06
     Gulf
    -0.06
    POSITIVE LOGITS
     layoutManager
    0.07
    BUR
    0.06
    season
    0.06
    Descriptor
    0.06
     Abdel
    0.06
    ступ
    0.06
    Generation
    0.06
     Мас
    0.06
    VertexAttribArray
    0.06
     NONINFRINGEMENT
    0.06
    Act Density 0.032%

    No Known Activations