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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’in
    -0.06
     Aş
    -0.06
    ’є
    -0.06
    anın
    -0.06
     WEEK
    -0.06
     ×
    -0.06
    단
    -0.06
     onc
    -0.06
    ınıf
    -0.06
     safezone
    -0.06
    POSITIVE LOGITS
     activating
    0.07
     deficient
    0.07
     magnetic
    0.06
     suicidal
    0.06
    oud
    0.06
    Tor
    0.06
     rob
    0.06
    265
    0.06
    /mat
    0.06
    .Arguments
    0.06
    Act Density 0.290%

    No Known Activations