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

    Neuronpedia

    INDEX
    Explanations

    develop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ponential
    -0.07
    _force
    -0.07
    hashCode
    -0.06
     catching
    -0.06
    ie
    -0.06
    GLOBAL
    -0.06
    blocking
    -0.06
     exponential
    -0.06
    azen
    -0.06
    Formatted
    -0.06
    POSITIVE LOGITS
    YS
    0.07
     byl
    0.06
    po
    0.06
    cen
    0.06
    ’ya
    0.06
    žít
    0.06
     almak
    0.06
    -expanded
    0.06
     tanto
    0.06
    .relationship
    0.06
    Act Density 0.045%

    No Known Activations