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

    Neuronpedia

    INDEX
    Explanations

    aries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PM
    -0.07
     hairs
    -0.07
     PEM
    -0.06
    меть
    -0.06
    _Struct
    -0.06
     chica
    -0.06
    _POP
    -0.06
    ılığ
    -0.06
    _measurement
    -0.06
    _corners
    -0.06
    POSITIVE LOGITS
     financing
    0.07
    Impact
    0.07
     tồn
    0.07
     Financing
    0.07
    ategori
    0.06
    osexual
    0.06
     पहल
    0.06
    方法
    0.06
    操作
    0.06
    افه
    0.06
    Act Density 0.000%

    No Known Activations