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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .byte
    -0.08
    INUE
    -0.07
    _shader
    -0.07
     Seconds
    -0.07
     serviceName
    -0.07
    ▘
    -0.07
     الرجل
    -0.07
    (queue
    -0.06
    _once
    -0.06
    ,callback
    -0.06
    POSITIVE LOGITS
     çıkar
    0.07
    擿
    0.06
     SAR
    0.06
    👟
    0.06
    雌
    0.06
    דר
    0.06
    от
    0.06
     어디
    0.06
     şü
    0.06
     pref
    0.06
    Act Density 0.004%

    No Known Activations