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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Heroes
    -0.07
    RESET
    -0.07
    Од
    -0.07
    Chrome
    -0.07
     UE
    -0.06
    _fatal
    -0.06
    Ni
    -0.06
    歯
    -0.06
    ีเด
    -0.06
     yok
    -0.06
    POSITIVE LOGITS
     постав
    0.06
    ятия
    0.06
     wenig
    0.06
     hacer
    0.06
    .Record
    0.06
    aking
    0.06
    _language
    0.06
    юн
    0.06
    (goal
    0.05
     quiere
    0.05
    Act Density 0.574%

    No Known Activations