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

    Neuronpedia

    INDEX
    Explanations

    Rights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ==="
    -0.07
    ];↵↵↵
    -0.07
    ###
    -0.07
    Have
    -0.06
    瑪
    -0.06
    arme
    -0.06
     Hum
    -0.06
     bin
    -0.06
    紫
    -0.06
     lavender
    -0.06
    POSITIVE LOGITS
    mongo
    0.08
    他又
    0.07
    راه
    0.07
    ὼ
    0.07
    łoż
    0.07
     Broad
    0.07
     asign
    0.07
    _months
    0.07
    _const
    0.07
    𝑗
    0.07
    Act Density 0.022%

    No Known Activations