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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =w
    -0.07
     Krist
    -0.07
    呵呵
    -0.07
    _Edit
    -0.07
    嘴
    -0.07
     rewritten
    -0.06
    גיד
    -0.06
    未经授权
    -0.06
    Slider
    -0.06
     modificar
    -0.06
    POSITIVE LOGITS
    inen
    0.07
    엊
    0.07
    四项
    0.07
    stag
    0.07
     bucket
    0.07
    _factor
    0.07
     styling
    0.06
    _SLEEP
    0.06
    ies
    0.06
     이렇게
    0.06
    Act Density 0.000%

    No Known Activations