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

    Neuronpedia

    INDEX
    Explanations

    Something could be worse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     murderer
    -0.08
     день
    -0.07
    になる
    -0.07
     builders
    -0.07
    Approved
    -0.07
    	range
    -0.07
    440
    -0.07
     Bullet
    -0.07
     Control
    -0.07
     ansch
    -0.07
    POSITIVE LOGITS
    FilePath
    0.06
     ph
    0.06
    ultiply
    0.06
    xac
    0.06
    лич
    0.06
     temperatura
    0.06
    .V
    0.06
     Сан
    0.06
     precisa
    0.06
    nement
    0.05
    Act Density 0.027%

    No Known Activations