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

    Neuronpedia

    INDEX
    Explanations

    Apologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     importantes
    -0.07
    inoa
    -0.07
    chema
    -0.06
    컬
    -0.06
     ure
    -0.06
    TRAIN
    -0.06
    LETED
    -0.06
    .local
    -0.06
    ountry
    -0.06
    _ENUM
    -0.06
    POSITIVE LOGITS
    Executable
    0.07
    halt
    0.06
     unfairly
    0.06
    'ét
    0.06
     hashed
    0.06
     occup
    0.06
     terre
    0.06
     нельзя
    0.06
     Biblical
    0.06
    }),
    0.06
    Act Density 0.012%

    No Known Activations