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

    Neuronpedia

    INDEX
    Explanations

    Initials and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xf
    -0.07
     whe
    -0.06
     XOR
    -0.06
    endedor
    -0.06
     ola
    -0.06
     tương
    -0.06
     declines
    -0.06
     Ingredient
    -0.06
     seedu
    -0.06
    ectors
    -0.06
    POSITIVE LOGITS
    (first
    0.07
    )(↵
    0.07
    travel
    0.07
    '''
↵
    0.07
     prep
    0.07
    enc
    0.07
    final
    0.06
    room
    0.06
    IDENT
    0.06
     virus
    0.06
    Act Density 0.007%

    No Known Activations