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

    Neuronpedia

    INDEX
    Explanations

    ratios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reform
    -0.07
     "<
    -0.07
    	local
    -0.07
     okol
    -0.07
    โล
    -0.07
    'icon
    -0.06
    –
    -0.06
     typography
    -0.06
    LOC
    -0.06
     maxx
    -0.06
    POSITIVE LOGITS
    _contact
    0.07
     Fibonacci
    0.06
     Unified
    0.06
    uelles
    0.06
    ераль
    0.06
    ENSIONS
    0.06
    PHY
    0.06
     kommen
    0.06
     atheist
    0.05
    ्भ
    0.05
    Act Density 0.007%

    No Known Activations