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

    Neuronpedia

    INDEX
    Explanations

    Radio

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marshal
    -0.08
     Photos
    -0.07
     trails
    -0.07
     Conservative
    -0.07
    יל
    -0.07
     radical
    -0.06
     marg
    -0.06
    acho
    -0.06
    合金
    -0.06
    Nothing
    -0.06
    POSITIVE LOGITS
    aepernick
    0.07
    คนไทย
    0.07
     ret
    0.06
    重回
    0.06
    阍
    0.06
    各行各业
    0.06
    ᆮ
    0.06
    힙
    0.06
    쾀
    0.06
    땀
    0.06
    Act Density 0.010%

    No Known Activations