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

    Neuronpedia

    INDEX
    Explanations

    academic courses or fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     says
    0.54
     r
    0.50
    0.46
     säga
    0.42
    lication
    0.42
     ఉపయోగ
    0.40
     ד
    0.39
     säger
    0.39
     några
    0.38
    âteau
    0.38
    POSITIVE LOGITS
    )$
    0.50
    O
    0.49
    학과
    0.48
    कू
    0.48
    𝘖
    0.47
    Students
    0.46
    তাহাদের
    0.46
     Đoàn
    0.46
     esemplari
    0.45
    Imperial
    0.45
    Act Density 0.309%

    No Known Activations