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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -pres
    -0.07
    udas
    -0.07
    塑
    -0.06
    認
    -0.06
     ctx
    -0.06
     الدم
    -0.06
    ernote
    -0.06
    IfExists
    -0.06
    _grp
    -0.06
     Niger
    -0.06
    POSITIVE LOGITS
     Reference
    0.07
     Venez
    0.07
     Belle
    0.07
     Kevin
    0.06
     architect
    0.06
     UFO
    0.06
     VAR
    0.06
     hexatrigesimal
    0.06
     thigh
    0.06
    roe
    0.06
    Act Density 0.008%

    No Known Activations