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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .CommandType
    -0.07
    忠
    -0.06
    /tags
    -0.06
    _Num
    -0.06
    contr
    -0.06
    Ja
    -0.06
    	target
    -0.06
    랫
    -0.06
     Rp
    -0.06
    265
    -0.06
    POSITIVE LOGITS
    '):
↵
    0.07
     localization
    0.07
     ödül
    0.06
     mình
    0.06
     Hermes
    0.06
    rací
    0.06
    �
    0.06
    itesse
    0.06
     결혼
    0.06
     pack
    0.06
    Act Density 0.005%

    No Known Activations