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

    Neuronpedia

    INDEX
    Explanations

    descriptive qualities and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ocellular
    0.40
     goblin
    0.39
    ponen
    0.39
     enumeration
    0.38
    unun
    0.38
    obar
    0.37
    ının
    0.37
    ether
    0.36
    olu
    0.36
    pw
    0.36
    POSITIVE LOGITS
    VA
    0.44
     aguas
    0.40
    ность
    0.40
     FRANCIS
    0.39
     Обра
    0.39
     акаде
    0.39
     রাজপ
    0.39
     राजीव
    0.38
     К
    0.38
    ไว
    0.38
    Act Density 0.001%

    No Known Activations