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

    Neuronpedia

    INDEX
    Explanations

    names followed by et al

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     computational
    0.35
     methodology
    0.34
     Nonlinear
    0.34
     methodological
    0.34
     invariants
    0.33
     kaleidoscopic
    0.32
     topologies
    0.32
    forschungs
    0.32
     reconstructing
    0.32
     thermodynam
    0.32
    POSITIVE LOGITS
     ও
    0.53
     и
    0.46
    และ
    0.44
     và
    0.43
     و
    0.39
     και
    0.39
     agus
    0.37
     et
    0.36
     ו
    0.36
     եւ
    0.35
    Act Density 0.003%

    No Known Activations