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

    Neuronpedia

    INDEX
    Explanations

    font

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rotational
    -0.07
     Sil
    -0.07
     обязан
    -0.07
     Regular
    -0.07
     boredom
    -0.06
    ικές
    -0.06
    時代
    -0.06
    rador
    -0.06
    最初
    -0.06
     abbrev
    -0.06
    POSITIVE LOGITS
     closest
    0.06
     schon
    0.06
     optimizer
    0.06
    ,file
    0.06
    entimes
    0.06
    ApiModelProperty
    0.06
    pike
    0.06
    	restore
    0.06
    ...
    0.06
     opciones
    0.06
    Act Density 0.009%

    No Known Activations