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

    Neuronpedia

    INDEX
    Explanations

    application

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oose
    -0.07
    \Unit
    -0.07
     plo
    -0.07
     clientele
    -0.07
     никто
    -0.06
    _longitude
    -0.06
    erguson
    -0.06
    oblins
    -0.06
    _REFER
    -0.06
    iu
    -0.06
    POSITIVE LOGITS
    ≠
    0.07
     с
    0.06
    -vis
    0.06
    .getClassName
    0.06
    /master
    0.06
    Phi
    0.06
     acción
    0.06
    ="{
    0.06
    λαμβ
    0.06
    Party
    0.06
    Act Density 0.037%

    No Known Activations