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

    Neuronpedia

    INDEX
    Explanations

    contractions like isn't don't it's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     configurable
    0.44
     standalone
    0.41
     scalable
    0.40
     TypeScript
    0.39
     usability
    0.38
     computed
    0.38
     nonprofit
    0.37
     software
    0.37
     মাঝারি
    0.37
     integrates
    0.36
    POSITIVE LOGITS
     murderous
    0.39
     guerra
    0.37
     humiliation
    0.36
     injustices
    0.35
     venge
    0.35
     guerre
    0.35
     betrayal
    0.34
    ья
    0.34
     legions
    0.33
     ненави
    0.33
    Act Density 0.077%

    No Known Activations