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

    Neuronpedia

    INDEX
    Explanations

    N

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    átor
    -0.07
    oncé
    -0.07
    Cargo
    -0.06
     goats
    -0.06
    andle
    -0.06
    /lib
    -0.06
     muži
    -0.06
     presents
    -0.06
    itat
    -0.06
     zm
    -0.06
    POSITIVE LOGITS
     ARISING
    0.06
     '',
↵
    0.06
    ='',
    0.06
    Young
    0.06
    .TODO
    0.06
    UBL
    0.06
    TECT
    0.06
    LogLevel
    0.06
     статус
    0.06
     EAR
    0.06
    Act Density 0.009%

    No Known Activations