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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igkeit
    -0.07
     heavyweight
    -0.07
     provád
    -0.07
     spectral
    -0.06
    prox
    -0.06
     Workshop
    -0.06
     enrol
    -0.06
     dipped
    -0.06
    unsigned
    -0.06
    __,
    -0.06
    POSITIVE LOGITS
    (MainActivity
    0.06
     قد
    0.06
    aec
    0.06
     POD
    0.06
     Fluent
    0.06
    700
    0.06
    ographically
    0.06
     Facial
    0.06
    AMI
    0.06
     motivating
    0.06
    Act Density 0.011%

    No Known Activations