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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ernaut
    -0.07
     causal
    -0.07
     lines
    -0.07
    ..↵↵
    -0.06
     caused
    -0.06
     repertoire
    -0.06
     meanwhile
    -0.06
    .isBlank
    -0.06
    ecret
    -0.06
    .Part
    -0.06
    POSITIVE LOGITS
    важа
    0.06
    toBeDefined
    0.06
    _FB
    0.06
    Domin
    0.06
    SUMER
    0.06
     yPos
    0.05
    사랑
    0.05
    tablet
    0.05
     सबस
    0.05
    0.05
    Act Density 0.002%

    No Known Activations