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

    Neuronpedia

    INDEX
    Explanations

    past states or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stava
    0.33
     filme
    0.31
     cinemat
    0.30
     filmes
    0.29
     condição
    0.29
     descrito
    0.28
    esimo
    0.27
    circ
    0.27
     quarta
    0.27
     principes
    0.27
    POSITIVE LOGITS
    Kong
    0.34
     .
    0.33
    Traditionally
    0.32
    作
    0.30
    Organization
    0.30
    Corpor
    0.30
    Speech
    0.30
    Like
    0.29
     Mobility
    0.29
    OND
    0.29
    Act Density 0.003%

    No Known Activations