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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     situation
    -0.07
     pl
    -0.06
     manifest
    -0.06
     Certain
    -0.06
    �
    -0.06
    %B
    -0.06
    pecific
    -0.06
    born
    -0.06
     situations
    -0.06
    VELO
    -0.06
    POSITIVE LOGITS
    IDDEN
    0.07
    .coeff
    0.07
    fdf
    0.07
     Driver
    0.06
    That
    0.06
     bodily
    0.06
    ombie
    0.06
    ест
    0.06
     dildo
    0.06
    ivamente
    0.06
    Act Density 0.036%

    No Known Activations