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

    Neuronpedia

    INDEX
    Explanations

    attackers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ~↵
    -0.07
    Price
    -0.07
    質
    -0.07
    -0.07
     Dial
    -0.07
    MaxLength
    -0.07
    .radians
    -0.06
    isory
    -0.06
    ratulations
    -0.06
    Baseline
    -0.06
    POSITIVE LOGITS
     loving
    0.07
     EI
    0.06
     greenhouse
    0.06
    .gr
    0.06
    ccione
    0.06
     erotico
    0.06
     recurse
    0.06
     sept
    0.06
    еними
    0.06
    _QU
    0.06
    Act Density 0.021%

    No Known Activations