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

    Neuronpedia

    INDEX
    Explanations

    Organization names/roles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的带领
    -0.07
    Sir
    -0.07
     Multimedia
    -0.07
    empor
    -0.07
    UBE
    -0.07
    ünst
    -0.07
    nea
    -0.06
    ཛ
    -0.06
    (figsize
    -0.06
    嵛
    -0.06
    POSITIVE LOGITS
    叹
    0.07
    
    0.07
     facing
    0.07
     collapsed
    0.07
    	hash
    0.07
    残酷
    0.07
     uncertain
    0.06
    :t
    0.06
     bay
    0.06
     today
    0.06
    Act Density 0.029%

    No Known Activations