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

    Neuronpedia

    INDEX
    Explanations

    programming/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ína
    -0.08
     uptime
    -0.07
    	push
    -0.07
    ;<
    -0.07
     flank
    -0.06
    従
    -0.06
    _fid
    -0.06
     �
    -0.06
    通信
    -0.06
     масло
    -0.06
    POSITIVE LOGITS
    UU
    0.07
    _perm
    0.07
     dee
    0.06
     McM
    0.06
     anti
    0.06
     кас
    0.06
    フ
    0.06
    655
    0.06
    530
    0.06
    _reader
    0.06
    Act Density 0.037%

    No Known Activations