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

    Neuronpedia

    INDEX
    Explanations

    not saying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     satisfied
    0.53
     obligated
    0.50
     interesados
    0.47
     compelled
    0.47
     deterred
    0.46
     motivated
    0.46
    satisfied
    0.46
     interested
    0.45
     obliged
    0.44
     заинтересо
    0.44
    POSITIVE LOGITS
     saying
    0.61
     suggesting
    0.61
     sugg
    0.56
     Saying
    0.55
    Suggest
    0.50
     Suggest
    0.50
     stating
    0.48
     sugger
    0.47
     decir
    0.44
     kval
    0.43
    Act Density 0.005%

    No Known Activations