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

    Neuronpedia

    INDEX
    Explanations

    top_p and temperature parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    offsetLeft
    0.42
    मारक
    0.40
    AgentError
    0.40
     latérales
    0.39
    Ơ
    0.39
    ArrayIndex
    0.39
    ResBuffer
    0.38
     шири
    0.38
    Lateral
    0.38
    肪
    0.38
    POSITIVE LOGITS
    top
    0.70
     top
    0.70
     Top
    0.59
     topp
    0.56
    Top
    0.53
     tops
    0.50
     トップ
    0.49
    tope
    0.47
    tops
    0.47
    トップ
    0.46
    Act Density 0.003%

    No Known Activations