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

    Neuronpedia

    INDEX
    Explanations

    list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    |^{
    0.44
    |"
    0.40
    interesse
    0.39
     Esp
    0.39
     Es
    0.38
     Essa
    0.37
    Es
    0.37
    ENTES
    0.37
    чета
    0.36
     eſ
    0.36
    POSITIVE LOGITS
    泪
    0.40
    Addr
    0.40
    Resume
    0.38
     Tolkien
    0.38
     அமை
    0.37
     AOL
    0.37
    нской
    0.37
     Blackwell
    0.36
     ദുൽ
    0.36
     अंतर
    0.36
    Act Density 0.000%

    No Known Activations