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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ascend
    -0.07
     malaria
    -0.07
    Consult
    -0.07
     actividades
    -0.06
    닫
    -0.06
    Jak
    -0.06
    돌
    -0.06
     najczęściej
    -0.06
     Volley
    -0.06
     CX
    -0.06
    POSITIVE LOGITS
    (lhs
    0.07
     constructor
    0.07
    _integral
    0.07
     aging
    0.07
     ва
    0.07
     viewport
    0.07
    save
    0.07
    resources
    0.07
    र
    0.07
    redicate
    0.07
    Act Density 0.005%

    No Known Activations