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

    Neuronpedia

    INDEX
    Explanations

    introductions and disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polytope
    0.29
     geometrical
    0.29
    ുകൾ
    0.29
     azimuthal
    0.28
     algoritmo
    0.28
     epoxide
    0.28
     monotonic
    0.27
     spectrophot
    0.27
     tvar
    0.26
     automaton
    0.26
    POSITIVE LOGITS
    there
    0.33
    they
    0.29
    edited
    0.29
    इसमें
    0.29
    ất
    0.28
     इसमें
    0.28
     They
    0.27
    academia
    0.27
     It
    0.27
    It
    0.27
    Act Density 0.720%

    No Known Activations