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

    Neuronpedia

    INDEX
    Explanations

    modes of interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াত্মক
    1.46
    -\
    1.27
    ag
    1.25
    la
    1.25
    ability
    1.21
     primi
    1.19
    জনক
    1.15
     мероприятия
    1.14
    j
    1.12
    दार
    1.11
    POSITIVE LOGITS
    isierung
    1.74
    dehyde
    1.73
    isieren
    1.63
    isatie
    1.54
    lly
    1.51
    िस्ट
    1.49
    ized
    1.47
    ب
    1.45
    izando
    1.44
    ização
    1.42
    Act Density 0.752%

    No Known Activations