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

    Neuronpedia

    INDEX
    Explanations

    mist curling around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    0.67
    c
    0.59
    r
    0.57
    p
    0.52
    0.51
    n
    0.50
    v
    0.47
    t
    0.45
    k
    0.43
        
    0.43
    POSITIVE LOGITS
     mistrust
    0.52
     اڈوں
    0.48
    FindingsResponse
    0.47
     بانک
    0.47
     紅
    0.46
     hunch
    0.46
     pessimism
    0.45
     paranoia
    0.45
     సర్
    0.44
     supposition
    0.43
    Act Density 0.000%

    No Known Activations