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
    �
    -0.06
     Jim
    -0.06
    Validity
    -0.06
     Single
    -0.06
    iu
    -0.06
    _CONT
    -0.06
     phù
    -0.06
     yellow
    -0.06
     carbs
    -0.06
    .af
    -0.06
    POSITIVE LOGITS
     uprav
    0.07
     embar
    0.06
    _merged
    0.06
    optic
    0.06
     góc
    0.06
     gyro
    0.06
     прибор
    0.06
    _jet
    0.06
    ха
    0.06
    ーク
    0.06
    Act Density 0.022%

    No Known Activations