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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ozřejmě
    -0.07
    stdClass
    -0.06
     acids
    -0.06
    antas
    -0.06
    .field
    -0.06
     Arte
    -0.06
     Born
    -0.06
    Commerce
    -0.06
    SMTP
    -0.06
     wholes
    -0.06
    POSITIVE LOGITS
     what
    0.07
     What
    0.07
     τρό
    0.07
    _link
    0.06
     �
    0.06
    .Reset
    0.06
    ael
    0.06
     WHAT
    0.06
    (remove
    0.06
    (predict
    0.06
    Act Density 0.035%

    No Known Activations