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

    Neuronpedia

    INDEX
    Explanations

    requirements, conditions, possibilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’ll
    -0.07
     authorized
    -0.07
     Rod
    -0.07
    (car
    -0.06
    'll
    -0.06
    _delivery
    -0.06
    ды
    -0.06
    "d
    -0.06
    _thumbnail
    -0.06
     may
    -0.06
    POSITIVE LOGITS
    aría
    0.07
     would
    0.07
     آموزش
    0.06
    oard
    0.06
     대전
    0.06
    �
    0.06
     Esta
    0.06
     Campo
    0.06
    .medium
    0.06
     OTP
    0.06
    Act Density 0.306%

    No Known Activations