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

    Neuronpedia

    INDEX
    Explanations

    keywords followed by related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     på
    0.45
    filled
    0.43
    erious
    0.43
    atschapp
    0.42
    human
    0.41
    oran
    0.41
    !.
    0.41
    isch
    0.40
    less
    0.40
    tik
    0.40
    POSITIVE LOGITS
     いく
    0.46
    開始
    0.42
     notes
    0.40
     ого
    0.39
     limbs
    0.38
    ቝ
    0.38
    ，“
    0.38
     ailment
    0.38
     ListItem
    0.37
     контакта
    0.37
    Act Density 0.058%

    No Known Activations