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

    Neuronpedia

    INDEX
    Explanations

    typed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minh
    -0.07
    _sa
    -0.07
    _PID
    -0.07
     ¬
    -0.06
     ab
    -0.06
     امام
    -0.06
    gradable
    -0.06
    .Generic
    -0.06
    fir
    -0.06
    arr
    -0.06
    POSITIVE LOGITS
     duż
    0.07
    verification
    0.07
    Jean
    0.07
    Sher
    0.06
    ....↵↵
    0.06
     Subscription
    0.06
    Tenant
    0.06
     Rutgers
    0.06
    .operations
    0.06
     bitter
    0.06
    Act Density 0.003%

    No Known Activations