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

    Neuronpedia

    INDEX
    Explanations

    mode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kobe
    -0.07
     Sanayi
    -0.06
    dob
    -0.06
    ponent
    -0.06
    ifik
    -0.06
    可能性
    -0.06
    근
    -0.06
    Sink
    -0.06
    .filename
    -0.06
    firm
    -0.06
    POSITIVE LOGITS
    agini
    0.08
     없음
    0.07
     flawed
    0.07
    .about
    0.07
     werden
    0.07
     Charles
    0.07
     chiếc
    0.07
     molding
    0.07
    (issue
    0.06
     یه
    0.06
    Act Density 0.007%

    No Known Activations