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

    Neuronpedia

    INDEX
    Explanations

    condition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     renaming
    -0.07
    消毒
    -0.07
     Adding
    -0.07
    iq
    -0.07
     simple
    -0.06
     iz
    -0.06
    .StObject
    -0.06
     ith
    -0.06
    usion
    -0.06
    Ƨ
    -0.06
    POSITIVE LOGITS
    .python
    0.07
    驾照
    0.07
    כנים
    0.07
    нал
    0.07
    _signals
    0.07
    (level
    0.07
     Trilogy
    0.07
     Drinks
    0.07
    LineStyle
    0.07
    xima
    0.07
    Act Density 0.015%

    No Known Activations