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

    Neuronpedia

    INDEX
    Explanations

    lockdown restrictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pec
    -0.07
     vocal
    -0.06
    تهم
    -0.06
    Cole
    -0.06
    zí
    -0.06
     Alternate
    -0.06
    FH
    -0.06
    DOUBLE
    -0.06
     Laurel
    -0.06
     Kế
    -0.06
    POSITIVE LOGITS
     wrestler
    0.06
    텔
    0.06
     SERVICES
    0.06
    比较
    0.06
     variance
    0.06
     capsules
    0.06
    /rc
    0.06
    /kg
    0.06
     collaborate
    0.06
    ення
    0.06
    Act Density 0.010%

    No Known Activations