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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SAT
    -0.07
    guest
    -0.07
    quite
    -0.06
     Quartz
    -0.06
    ZW
    -0.06
    Decoder
    -0.06
     birthday
    -0.06
     Scheduler
    -0.06
     advisory
    -0.06
    aghetti
    -0.05
    POSITIVE LOGITS
    —and
    0.07
     "'");↵
    0.07
     ElseIf
    0.07
     форми
    0.07
    hash
    0.07
     tid
    0.06
    ème
    0.06
     움직
    0.06
     복
    0.06
     Hollande
    0.06
    Act Density 0.024%

    No Known Activations