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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spouses
    -0.09
    Sex
    -0.08
    _EDGE
    -0.08
    莲花
    -0.08
    _VOICE
    -0.07
    Other
    -0.07
     Pivot
    -0.07
     edited
    -0.07
    -download
    -0.07
     companyId
    -0.07
    POSITIVE LOGITS
    3
    0.07
    _SPE
    0.07
    מסר
    0.07
    𝙡
    0.07
    �
    0.07
    0.07
    Գ
    0.06
     dn
    0.06
    -so
    0.06
    SG
    0.06
    Act Density 0.153%

    No Known Activations