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

    Neuronpedia

    INDEX
    Explanations

    future statements of intent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    แจ
    0.40
     могу
    0.39
     ဟ
    0.39
    顔
    0.38
     μπορού
    0.38
     הד
    0.38
     भले
    0.38
    鋃
    0.37
     பர
    0.37
     makeSound
    0.37
    POSITIVE LOGITS
     doubtless
    0.60
     no
    0.58
     shortly
    0.54
     देंगे
    0.52
     normally
    0.48
     olisi
    0.47
     habría
    0.46
     envisage
    0.46
     need
    0.45
     होईल
    0.45
    Act Density 0.002%

    No Known Activations