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

    Neuronpedia

    INDEX
    Explanations

    directions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _character
    -0.07
     Awareness
    -0.07
    _reset
    -0.06
    _CAPACITY
    -0.06
     specifies
    -0.06
    rowable
    -0.06
     diag
    -0.06
    ูล
    -0.06
     csv
    -0.06
    .exception
    -0.06
    POSITIVE LOGITS
     ladies
    0.07
    edom
    0.06
    mailto
    0.06
    South
    0.06
    .bp
    0.06
     hedef
    0.06
    Rp
    0.06
     underscore
    0.06
    亦
    0.06
    ด
    0.06
    Act Density 0.004%

    No Known Activations