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

    Neuronpedia

    INDEX
    Explanations

    Plan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     улы
    -0.07
    center
    -0.07
    .Constant
    -0.07
     mime
    -0.07
    .od
    -0.06
     MIME
    -0.06
     Su
    -0.06
     Slam
    -0.06
    (op
    -0.06
    -fr
    -0.06
    POSITIVE LOGITS
    adget
    0.07
     listing
    0.06
    Arg
    0.06
    AppState
    0.06
     YEARS
    0.06
    ipur
    0.06
    _Map
    0.05
    čná
    0.05
    户
    0.05
    cker
    0.05
    Act Density 0.020%

    No Known Activations