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

    Neuronpedia

    INDEX
    Explanations

    STEM fields and education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.46
     minimization
    0.38
     that
    0.38
     thereof
    0.38
    abulous
    0.37
    ordination
    0.37
    keyup
    0.36
    riterion
    0.36
    get
    0.35
    gevity
    0.35
    POSITIVE LOGITS
     STEM
    0.51
    STEM
    0.49
    روس
    0.44
     सामग्री
    0.43
    <unused2200>
    0.41
     আত্মীয়
    0.40
    Materials
    0.40
    𝐢
    0.40
    Dates
    0.40
     أ
    0.40
    Act Density 0.001%

    No Known Activations