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

    Neuronpedia

    INDEX
    Explanations

    “ Clearly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    感
    0.39
     छोर
    0.38
     testname
    0.36
    épaisseur
    0.36
     שכ
    0.36
    孙
    0.36
    流
    0.36
    Ant
    0.35
    ertown
    0.35
     سن
    0.34
    POSITIVE LOGITS
     populated
    0.42
     Вы
    0.41
     Eucalyptus
    0.40
     Relativity
    0.39
     fiddle
    0.38
     Australia
    0.38
     Referring
    0.38
     instance
    0.37
     TT
    0.37
     “
    0.37
    Act Density 0.000%

    No Known Activations