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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     faculty
    -0.06
     공개
    -0.06
     understood
    -0.06
    chemas
    -0.06
     trace
    -0.06
     해야
    -0.06
     primary
    -0.06
     윤
    -0.06
     непри
    -0.06
    ‹
    -0.06
    POSITIVE LOGITS
    mf
    0.06
    _Device
    0.06
    Initialization
    0.06
    ingerprint
    0.06
    $html
    0.06
     університет
    0.06
     #-
    0.06
     multiplication
    0.06
     dlouhodob
    0.06
     stereo
    0.06
    Act Density 0.026%

    No Known Activations