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

    Neuronpedia

    INDEX
    Explanations

    life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quanto
    -0.06
     зна
    -0.06
     gelen
    -0.06
     ему
    -0.06
     переш
    -0.06
     annoying
    -0.06
    DAT
    -0.06
    ,default
    -0.06
     Redskins
    -0.06
    herited
    -0.06
    POSITIVE LOGITS
    .Package
    0.07
    etch
    0.06
    イ
    0.06
    LOY
    0.06
     ingestion
    0.06
    allee
    0.06
     stimulate
    0.06
     Union
    0.06
    (""))↵
    0.06
    .Action
    0.06
    Act Density 0.005%

    No Known Activations