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

    Neuronpedia

    INDEX
    Explanations

    OS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﯾ
    -0.07
    심
    -0.07
     "&
    -0.07
    𝔅
    -0.07
    变身
    -0.07
     Henderson
    -0.07
     penchant
    -0.07
    (View
    -0.07
    ㊟
    -0.07
    ❗
    -0.07
    POSITIVE LOGITS
     diploma
    0.07
    _unicode
    0.07
     deform
    0.07
     Ре
    0.07
     refugees
    0.07
     Probe
    0.07
    0.07
    داعش
    0.07
    significant
    0.07
    \[
    0.06
    Act Density 0.006%

    No Known Activations