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

    Neuronpedia

    INDEX
    Explanations

    academic publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _storage
    -0.06
    Comfort
    -0.06
    _character
    -0.06
    aştır
    -0.06
     Bath
    -0.06
     alespoň
    -0.06
    상의
    -0.06
     nive
    -0.06
     Script
    -0.06
    らの
    -0.06
    POSITIVE LOGITS
     Proceedings
    0.07
     conventions
    0.07
    Rev
    0.06
     iht
    0.06
     convention
    0.06
    _DET
    0.06
     }}↵
    0.06
    riott
    0.06
    etro
    0.06
    mates
    0.06
    Act Density 0.003%

    No Known Activations