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

    Neuronpedia

    INDEX
    Explanations

    probability calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Combat
    -0.07
    aud
    -0.06
     whence
    -0.06
    _pd
    -0.06
     města
    -0.06
    Ћ
    -0.06
    Ố
    -0.06
    \Application
    -0.06
     ForCanBeConverted
    -0.05
     เร
    -0.05
    POSITIVE LOGITS
     lovely
    0.07
     đẹp
    0.07
     zajist
    0.07
     healthcare
    0.06
     discard
    0.06
     sorry
    0.06
     Beauty
    0.06
    Greek
    0.06
    -important
    0.06
     Globe
    0.06
    Act Density 0.002%

    No Known Activations