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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	screen
    -0.07
    .tensor
    -0.07
     Lo
    -0.06
    .Session
    -0.06
    bbing
    -0.06
     vaccinations
    -0.06
    &B
    -0.06
    	cur
    -0.06
    _lock
    -0.06
    Mah
    -0.06
    POSITIVE LOGITS
     Pag
    0.07
     còn
    0.07
     труб
    0.06
     groove
    0.06
    同
    0.06
     такие
    0.06
     evolving
    0.06
     Survivor
    0.06
     동안
    0.06
    тех
    0.06
    Act Density 0.102%

    No Known Activations