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

    Neuronpedia

    INDEX
    Explanations

    mode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     अफ
    -0.06
    	double
    -0.06
    Data
    -0.06
     paste
    -0.06
     blender
    -0.06
     Yak
    -0.06
     yog
    -0.06
    care
    -0.06
    Af
    -0.06
    orris
    -0.06
    POSITIVE LOGITS
    χία
    0.07
     dispozici
    0.07
     farklı
    0.06
    주는
    0.06
    elial
    0.06
    付き
    0.06
    -await
    0.06
    TRL
    0.06
    EDIATE
    0.06
    ์ช
    0.06
    Act Density 0.016%

    No Known Activations