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

    Neuronpedia

    INDEX
    Explanations

    legal and technical document sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    二维
    0.48
    őt
    0.47
     islets
    0.47
    োজেন
    0.47
    呕
    0.47
    cimiento
    0.46
     MyRegisterClass
    0.46
    敒
    0.46
    ritable
    0.46
     იყოს
    0.46
    POSITIVE LOGITS
    à
    0.44
     STYLE
    0.40
    ati
    0.39
    SON
    0.38
    SER
    0.38
     stylu
    0.38
    ギア
    0.38
     beck
    0.37
    8
    0.37
     belle
    0.37
    Act Density 0.000%

    No Known Activations