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

    Neuronpedia

    INDEX
    Explanations

    across the front

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     megfelel
    0.57
     altres
    0.49
     intérieur
    0.48
    𝔪
    0.46
     familien
    0.45
     ähn
    0.44
     italien
    0.43
     grupa
    0.43
     weer
    0.43
     itali
    0.43
    POSITIVE LOGITS
    Blade
    0.54
     blade
    0.49
     Blade
    0.49
    Phrase
    0.49
    functioning
    0.48
    Ist
    0.48
    Gray
    0.48
    blade
    0.47
    ко
    0.46
    Phantom
    0.46
    Act Density 0.000%

    No Known Activations