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

    Neuronpedia

    INDEX
    Explanations

    annuities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    牺
    -0.07
    办好
    -0.07
    Mapped
    -0.07
    анд
    -0.06
     consul
    -0.06
     zb
    -0.06
     damage
    -0.06
    つい
    -0.06
     '
↵
    -0.06
    发布会
    -0.06
    POSITIVE LOGITS
    出汗
    0.08
     Dogs
    0.07
    Ess
    0.07
    zeigen
    0.07
    	settings
    0.07
    \">
    0.07
    视听节目
    0.07
    _edge
    0.06
    _ES
    0.06
    escription
    0.06
    Act Density 0.006%

    No Known Activations