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

    Neuronpedia

    INDEX
    Explanations

    code/markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avic
    -0.07
    jal
    -0.07
     develops
    -0.06
     bailout
    -0.06
     Δημο
    -0.06
    ало
    -0.06
    .Compute
    -0.06
    /avatar
    -0.06
     Bool
    -0.06
     ratios
    -0.06
    POSITIVE LOGITS
    _green
    0.07
    cold
    0.06
    <![
    0.06
     Mist
    0.06
     ประ
    0.06
     leisure
    0.06
    Mass
    0.06
    ляются
    0.06
     گذاری
    0.06
     coordin
    0.06
    Act Density 0.035%

    No Known Activations