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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hat
    -0.07
    VL
    -0.07
     calmly
    -0.06
    RL
    -0.06
    azel
    -0.06
     Sak
    -0.06
    buf
    -0.06
    .hot
    -0.06
    oux
    -0.06
    isto
    -0.06
    POSITIVE LOGITS
    藥
    0.07
     ميل
    0.06
    “.
    0.06
     gmail
    0.06
    .RES
    0.06
     github
    0.06
     přev
    0.06
    _PRIV
    0.06
     інтерес
    0.06
    _tbl
    0.06
    Act Density 0.000%

    No Known Activations