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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jon
    -0.08
     regeneration
    -0.07
    	direction
    -0.07
     arise
    -0.07
     Dynamics
    -0.07
     Unix
    -0.07
    .Url
    -0.06
     grenades
    -0.06
    زد
    -0.06
    Fail
    -0.06
    POSITIVE LOGITS
     MET
    0.08
    _[
    0.06
     eyed
    0.06
     Đại
    0.06
     cinsel
    0.06
    /em
    0.06
    ilogue
    0.06
    ราช
    0.05
     Navigator
    0.05
    conditional
    0.05
    Act Density 0.050%

    No Known Activations