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

    Neuronpedia

    INDEX
    Explanations

    OT

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     closer
    -0.07
     tribal
    -0.07
     tĩnh
    -0.07
    _terminal
    -0.06
     probs
    -0.06
     إن
    -0.06
    itan
    -0.06
    cols
    -0.06
    ")+
    -0.06
    曈
    -0.06
    POSITIVE LOGITS
    Resources
    0.07
    _qu
    0.07
    _Count
    0.07
    0.07
    供
    0.06
     hide
    0.06
    SEQU
    0.06
    מעניק
    0.06
    shaled
    0.06
    asing
    0.06
    Act Density 0.000%

    No Known Activations