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

    Neuronpedia

    INDEX
    Explanations

    mental health, cost pain, free

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CH
    0.48
    I
    0.47
    ANGE
    0.46
    ANE
    0.44
    G
    0.43
    Able
    0.42
    ILA
    0.42
    ABLE
    0.41
    En
    0.40
     ಎ
    0.40
    POSITIVE LOGITS
    ogén
    0.58
    rógeno
    0.51
     चौराहे
    0.49
    踽
    0.46
     நிவார
    0.45
    ுற
    0.45
     दुल्हन
    0.45
     attains
    0.44
    ளின்
    0.43
    coons
    0.43
    Act Density 0.001%

    No Known Activations