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

    Neuronpedia

    INDEX
    Explanations

    similarity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fatto
    -0.07
    �
    -0.07
    Our
    -0.07
     Cas
    -0.07
    Forms
    -0.07
    StackTrace
    -0.07
     été
    -0.07
     cruising
    -0.07
     sempre
    -0.06
    addy
    -0.06
    POSITIVE LOGITS
    -rad
    0.07
    (deg
    0.07
    VEL
    0.07
     indeb
    0.06
    unexpected
    0.06
     disqualified
    0.06
    omanip
    0.06
    tabla
    0.06
     bekommen
    0.06
     смер
    0.06
    Act Density 0.027%

    No Known Activations