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

    Neuronpedia

    INDEX
    Explanations

    worth, worthlessness, worsens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nutzen
    0.46
    ITU
    0.41
     حيث
    0.41
     Voices
    0.41
     Nähe
    0.41
     термин
    0.41
    "]]
    0.41
     Necessary
    0.40
    irman
    0.40
     Further
    0.40
    POSITIVE LOGITS
    kipun
    0.49
    esley
    0.47
    cester
    0.46
     enemy
    0.44
    pleo
    0.44
    fulness
    0.43
     worsening
    0.42
     adversary
    0.41
    gewood
    0.41
    worthiness
    0.41
    Act Density 0.007%

    No Known Activations