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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    view
    -0.07
    (cmp
    -0.07
     gpu
    -0.06
    340
    -0.06
     signed
    -0.06
    face
    -0.06
    banks
    -0.06
    Việc
    -0.06
     configurations
    -0.06
     theft
    -0.06
    POSITIVE LOGITS
     juste
    0.07
     './../../
    0.07
     getCategory
    0.06
     ragazzi
    0.06
     startActivity
    0.06
     MISS
    0.06
    .boost
    0.06
     яб
    0.06
    _wrong
    0.06
    handleSubmit
    0.06
    Act Density 0.032%

    No Known Activations