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

    Neuronpedia

    INDEX
    Explanations

    obstacle

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    329
    -0.07
    _names
    -0.07
    inz
    -0.07
    _loader
    -0.07
    IN
    -0.07
     заяв
    -0.06
    .getById
    -0.06
     bao
    -0.06
     original
    -0.06
    in
    -0.06
    POSITIVE LOGITS
    _RO
    0.07
    (Route
    0.07
    ге
    0.07
     obstacle
    0.06
     кож
    0.06
    ropy
    0.06
     Ay
    0.06
     �
    0.06
    周年
    0.06
    egg
    0.06
    Act Density 0.009%

    No Known Activations