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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serge
    -0.07
     Het
    -0.07
    _ACCEPT
    -0.07
    河
    -0.07
     Atmos
    -0.07
    .marker
    -0.07
     PREFIX
    -0.06
     Fuk
    -0.06
     echoing
    -0.06
     zenith
    -0.06
    POSITIVE LOGITS
    θηκε
    0.06
    -writing
    0.06
     Lebanese
    0.06
     OnInit
    0.06
    ĞI
    0.06
     lucrative
    0.06
     piger
    0.06
    렸
    0.06
    errupted
    0.06
    üml
    0.06
    Act Density 0.041%

    No Known Activations