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

    Neuronpedia

    INDEX
    Explanations

    HTML grid layouts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Con
    -0.07
     Bust
    -0.06
    whose
    -0.06
     Cuisine
    -0.06
     cost
    -0.06
     submarine
    -0.06
     exploiting
    -0.06
    .Return
    -0.06
    .period
    -0.06
    .Pop
    -0.06
    POSITIVE LOGITS
     annunci
    0.07
    formace
    0.07
     reluct
    0.06
    ВА
    0.06
     notoriously
    0.06
     možná
    0.06
    '|
    0.06
     лютого
    0.06
    .EditText
    0.06
     nakne
    0.06
    Act Density 0.022%

    No Known Activations