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

    Neuronpedia

    INDEX
    Explanations

    Numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indicators
    -0.07
     sentient
    -0.06
     ona
    -0.06
     умов
    -0.06
    _extent
    -0.06
    ／／／／
    -0.06
    WIN
    -0.06
     minLength
    -0.06
    win
    -0.06
     servicios
    -0.06
    POSITIVE LOGITS
     LDAP
    0.07
    _MSB
    0.07
     happ
    0.06
    Qi
    0.06
    ेटर
    0.06
     engel
    0.06
    應
    0.06
    _FILL
    0.06
    _coupon
    0.06
    nite
    0.05
    Act Density 0.097%

    No Known Activations