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

    Neuronpedia

    INDEX
    Explanations

    groups of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     settings
    0.49
     powertrain
    0.46
     ethically
    0.43
     downright
    0.42
     plugged
    0.42
     куда
    0.42
     synced
    0.41
     mixed
    0.41
     kế
    0.41
     mingled
    0.41
    POSITIVE LOGITS
     théâtre
    0.51
     médicament
    0.50
    ㈣
    0.49
     avem
    0.48
     teatral
    0.47
     مدرس
    0.46
     complej
    0.45
    ادث
    0.45
    മിതി
    0.45
     Pren
    0.44
    Act Density 0.005%

    No Known Activations