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

    Neuronpedia

    INDEX
    Explanations

    exceptions and constraints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    éc
    -0.08
    .medium
    -0.07
     mezcla
    -0.07
    ovanja
    -0.07
    écution
    -0.07
    zhou
    -0.07
    vest
    -0.07
    Vest
    -0.07
     데이터를
    -0.07
     Medio
    -0.07
    POSITIVE LOGITS
     kuphela
    0.10
     sahaja
    0.09
     sanctioned
    0.09
     permitted
    0.09
     sebag
    0.09
     ocasião
    0.09
     occasion
    0.09
     authorized
    0.08
    Occurred
    0.08
    ापुर
    0.08
    Act Density 0.011%

    No Known Activations