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

    Neuronpedia

    INDEX
    Explanations

    limits and extreme values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     negoti
    -0.08
     pendiente
    -0.07
    抽
    -0.07
     comentarios
    -0.07
    เฟ
    -0.07
     ethical
    -0.07
     ngu
    -0.07
     ಮಾ�
    -0.07
     trunc
    -0.07
     exch
    -0.07
    POSITIVE LOGITS
     CRO
    0.09
     Peaks
    0.09
    -around
    0.09
     peaked
    0.09
     peaks
    0.09
    aruh
    0.08
     LOW
    0.08
     rundt
    0.08
    ിങ്ങ
    0.08
     trás
    0.08
    Act Density 0.041%

    No Known Activations