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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Intent
    -0.07
    "M
    -0.07
    Disposed
    -0.07
    .ReLU
    -0.06
    _secure
    -0.06
     povol
    -0.06
    reject
    -0.06
    hint
    -0.06
     invalidate
    -0.06
    Mil
    -0.06
    POSITIVE LOGITS
    .transition
    0.06
    .getResources
    0.06
    чний
    0.06
    傷
    0.06
    .jface
    0.06
     कथ
    0.06
     Pyramid
    0.05
     Levin
    0.05
    イヤ
    0.05
    getDate
    0.05
    Act Density 0.000%

    No Known Activations