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

    Neuronpedia

    INDEX
    Explanations

    mechanic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hatta
    -0.08
     تغییر
    -0.07
    *@
    -0.07
    Discuss
    -0.06
    jadi
    -0.06
     đĩa
    -0.06
    )\
    -0.06
    hasOne
    -0.06
    etting
    -0.06
    Without
    -0.06
    POSITIVE LOGITS
     mechanic
    0.27
    ωτερ
    0.07
    allest
    0.07
    0.07
    ="/">↵
    0.07
     Mechan
    0.06
     Ming
    0.06
    jenis
    0.06
    ombre
    0.06
    _const
    0.06
    Act Density 0.001%

    No Known Activations