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

    Neuronpedia

    INDEX
    Explanations

    Additionally,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %;
    -1.57
    }]
    -1.45
     następnie
    -1.43
     Aufenthalt
    -1.40
    नलोड
    -1.39
    %;
    -1.33
    يح
    -1.32
     Ancak
    -1.31
     faldas
    -1.30
     });
    -1.28
    POSITIVE LOGITS
    ,
    1.76
     they
    1.40
     decisão
    1.38
     专业
    1.37
    咲き
    1.32
    ti
    1.32
     certaines
    1.30
    _
    1.30
     castig
    1.29
     传统
    1.29
    Act Density 0.017%

    No Known Activations