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

    Neuronpedia

    INDEX
    Explanations

    physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .date
    -0.07
    .condition
    -0.07
    urse
    -0.07
    _place
    -0.06
    .MSG
    -0.06
     suing
    -0.06
    .vs
    -0.06
    间
    -0.06
    ивает
    -0.06
    miş
    -0.06
    POSITIVE LOGITS
    350
    0.07
     transported
    0.06
     Appears
    0.06
    čka
    0.06
     conten
    0.06
     Port
    0.06
    30
    0.06
     Çev
    0.06
     Getting
    0.06
     canine
    0.06
    Act Density 0.007%

    No Known Activations