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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scholars
    -0.07
    怪
    -0.06
     fishes
    -0.06
     DNA
    -0.06
     [('
    -0.06
    VD
    -0.06
    _pkg
    -0.06
     Scotch
    -0.06
     Fax
    -0.06
    .started
    -0.06
    POSITIVE LOGITS
     Nutzung
    0.07
     ένα
    0.07
    Tipo
    0.07
    帰
    0.07
    :";↵
    0.07
    áci
    0.06
     getattr
    0.06
     unas
    0.06
    chandle
    0.06
    //↵↵↵
    0.06
    Act Density 0.024%

    No Known Activations