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

    Neuronpedia

    INDEX
    Explanations

    possessive and contracted forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ırd
    0.46
     کرمان
    0.45
     compensating
    0.44
    ließt
    0.43
     identifying
    0.43
     explosive
    0.43
    ようになる
    0.43
    ัญหา
    0.43
     declining
    0.43
    ục
    0.42
    POSITIVE LOGITS
     cun
    0.52
     المض
    0.51
     mant
    0.49
     maestros
    0.48
    М
    0.48
     Же
    0.47
     agr
    0.46
    헨
    0.45
     bara
    0.45
     diethyl
    0.45
    Act Density 0.079%

    No Known Activations