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

    Neuronpedia

    INDEX
    Explanations

    actions and qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etos
    0.42
     disrespectful
    0.40
     earum
    0.40
     dijel
    0.39
    戞
    0.39
    किशोर
    0.38
     murdered
    0.38
    する方法
    0.38
    atar
    0.38
     उनमें
    0.38
    POSITIVE LOGITS
     collapsible
    0.45
     Outlook
    0.39
     ತು
    0.39
     accents
    0.39
     nanotubes
    0.38
     nematodes
    0.38
    AutoComplete
    0.38
     indors
    0.37
     State
    0.37
    Outlook
    0.37
    Act Density 0.000%

    No Known Activations