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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     ihre
    -0.06
     širo
    -0.06
    )),↵
    -0.06
     �
    -0.06
    .br
    -0.06
    Throw
    -0.06
    ุคคล
    -0.06
    >p
    -0.06
    ’S
    -0.06
    POSITIVE LOGITS
    blend
    0.08
    .Compare
    0.07
    .vector
    0.07
     differentiate
    0.07
    .eclipse
    0.07
    ći
    0.07
    ồn
    0.07
    quisite
    0.07
    Milliseconds
    0.06
    iesta
    0.06
    Act Density 0.046%

    No Known Activations