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

    Neuronpedia

    INDEX
    Explanations

    online text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    issued
    -0.28
    è¯įæĿ¡
    -0.26
    ofile
    -0.25
     string
    -0.25
     Chapel
    -0.24
    (ss
    -0.24
    apult
    -0.23
    otel
    -0.23
    atches
    -0.23
    coc
    -0.23
    POSITIVE LOGITS
    å°±çŁ¥éģĵ
    0.28
    ncias
    0.27
    pires
    0.26
    çĸĶ
    0.25
    å°±èĥ½
    0.25
    人æ°ijæľįåĬ¡
    0.25
    prend
    0.24
    å°±èĥ½å¤Ł
    0.24
    erre
    0.24
    éŁª
    0.24
    Act Density 0.001%

    No Known Activations