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

    Neuronpedia

    INDEX
    Explanations

    Opinions/reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _la
    -0.07
    alist
    -0.07
    inema
    -0.07
     revolutions
    -0.07
     ECS
    -0.07
    positor
    -0.07
     freshman
    -0.07
    穿
    -0.06
     Eh
    -0.06
    layer
    -0.06
    POSITIVE LOGITS
    .visible
    0.08
     handleChange
    0.07
    (rank
    0.06
    ักด
    0.06
    .basic
    0.06
     ifndef
    0.06
     нали
    0.06
    InputChange
    0.06
    .Down
    0.06
     standard
    0.06
    Act Density 0.083%

    No Known Activations