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

    Neuronpedia

    INDEX
    Explanations

    game object material

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     继续
    0.63
     உலகம்
    0.62
     Framework
    0.59
     તેની
    0.55
     dimensione
    0.55
     quede
    0.54
     steril
    0.54
     horizont
    0.53
    ilized
    0.53
     horizontal
    0.52
    POSITIVE LOGITS
    ла
    0.55
    다
    0.55
    ակ
    0.53
    льную
    0.52
    }$,
    0.50
    را
    0.50
    strategy
    0.50
    ബരിമല
    0.50
    strategies
    0.49
    u
    0.49
    Act Density 0.007%

    No Known Activations