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

    Neuronpedia

    INDEX
    Explanations

    statements about informing decision-making, development, or research efforts

    oai_token-act-pair · gemini-2.0-flash

    inform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     officiers
    -0.54
    gesetz
    -0.49
     maksi
    -0.45
    nextDouble
    -0.44
    ntgen
    -0.43
     concealed
    -0.42
     sprá
    -0.42
     tố
    -0.42
     depósito
    -0.42
     Ingram
    -0.41
    POSITIVE LOGITS
     متعلقه
    0.85
    CPtr
    0.79
     saites
    0.79
     صوتيه
    0.77
    AutoScaleMode
    0.76
     AssemblyCompany
    0.76
    KommentareTeilen
    0.75
    rrggbb
    0.74
     autorytatywna
    0.74
    ImageContext
    0.73
    Act Density 1.663%

    No Known Activations