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

    Neuronpedia

    INDEX
    Explanations

    again, again, again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अर्थात
    0.37
     presumably
    0.34
     assunto
    0.33
    prong
    0.33
    presumably
    0.33
    意
    0.32
    䀎
    0.32
    rente
    0.32
    ப்பட்டது
    0.32
    ദന
    0.31
    POSITIVE LOGITS
     again
    0.75
    again
    0.70
     with
    0.63
     mutta
    0.61
     novamente
    0.59
     আবার
    0.59
     पुन्हा
    0.58
     secondaires
    0.58
     nhưng
    0.58
     Again
    0.57
    Act Density 0.099%

    No Known Activations