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

    Neuronpedia

    INDEX
    Explanations

    true/verdadera history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     percib
    0.45
     Adj
    0.38
     spinoff
    0.38
    ほうが
    0.37
     aastal
    0.36
    后缀
    0.36
    కుంటు
    0.36
     svim
    0.36
     Dixie
    0.36
     Skid
    0.36
    POSITIVE LOGITS
    INDOW
    0.42
    Honor
    0.40
    honor
    0.40
    PROGRAM
    0.39
    anyan
    0.38
    శ్
    0.38
    GridLayout
    0.38
    ρός
    0.37
    これ
    0.37
    真正
    0.36
    Act Density 0.001%

    No Known Activations