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

    Neuronpedia

    INDEX
    Explanations

    isolation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いろんな
    0.85
    นี้
    0.80
     hypothes
    0.80
     reorgan
    0.79
    㓡
    0.77
    la
    0.76
    㫙
    0.76
    茷
    0.75
    䇢
    0.75
    稦
    0.75
    POSITIVE LOGITS
    Isolation
    1.23
    AN
    1.21
     isolation
    1.14
    .
    1.12
     Isolation
    1.10
    AT
    1.09
     aisl
    1.02
    Isolated
    1.02
    IN
    0.98
    TE
    0.96
    Act Density 0.010%

    No Known Activations