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

    Neuronpedia

    INDEX
    Explanations

    etymology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     retract
    -0.07
    개월
    -0.06
    Disp
    -0.06
     bathtub
    -0.06
    reat
    -0.06
    τερο
    -0.06
    622
    -0.06
    COLUMN
    -0.06
    dimensions
    -0.06
    asco
    -0.06
    POSITIVE LOGITS
    .ReLU
    0.07
     mana
    0.07
    `,`
    0.06
     równ
    0.06
    _quota
    0.06
    qué
    0.06
     overseeing
    0.06
     масла
    0.06
    |array
    0.06
    ài
    0.06
    Act Density 0.018%

    No Known Activations