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

    Neuronpedia

    INDEX
    Explanations

    29

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    唱
    -0.07
    �
    -0.07
    <(),
    -0.06
     Lia
    -0.06
     coward
    -0.06
    '],
    -0.06
     सत
    -0.06
    ない
    -0.06
    /cupertino
    -0.06
    _stdio
    -0.06
    POSITIVE LOGITS
    Url
    0.07
     Daughter
    0.07
     optimizing
    0.06
    ;
↵
↵
↵
↵
    0.06
    -project
    0.06
    Obj
    0.06
     Overall
    0.06
    =json
    0.06
     proble
    0.06
     chr
    0.06
    Act Density 0.005%

    No Known Activations