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

    Neuronpedia

    INDEX
    Explanations

    names of notable people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Brandenburg
    0.41
     Stationary
    0.37
    沽
    0.37
    ക്കാരി
    0.37
     एना
    0.37
    libat
    0.36
     Enzym
    0.36
    ╫
    0.35
     Abra
    0.35
     Crunchy
    0.35
    POSITIVE LOGITS
     OBE
    0.85
     CBE
    0.71
     OM
    0.68
     MBE
    0.66
     OP
    0.66
     AO
    0.61
    OP
    0.60
     DBE
    0.59
     OS
    0.59
     CS
    0.59
    Act Density 0.004%

    No Known Activations