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

    Neuronpedia

    INDEX
    Explanations

    symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ʬ
    -0.07
    难过
    -0.07
    ທ
    -0.07
     influential
    -0.07
    blob
    -0.07
    ❪
    -0.07
    🥶
    -0.07
    .command
    -0.06
     Sunny
    -0.06
    輝
    -0.06
    POSITIVE LOGITS
     tightening
    0.07
    ........
    0.06
     EM
    0.06
    constant
    0.06
    处置
    0.06
    Floating
    0.06
    לילה
    0.06
    掛け
    0.06
     microbi
    0.06
     Make
    0.06
    Act Density 0.032%

    No Known Activations