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

    Neuronpedia

    INDEX
    Explanations

    Indian culture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    が
    -0.07
     elemento
    -0.07
     MY
    -0.06
     Johnston
    -0.06
    ı
    -0.06
    guards
    -0.06
    }>
    -0.06
     Mur
    -0.06
    他們
    -0.06
     continuum
    -0.06
    POSITIVE LOGITS
    paněl
    0.07
     каль
    0.07
    alk
    0.07
    éal
    0.07
     �
    0.07
    _FILENO
    0.07
    juven
    0.06
    alking
    0.06
    _PAYLOAD
    0.06
    ivated
    0.06
    Act Density 0.006%

    No Known Activations