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

    Neuronpedia

    INDEX
    Explanations

    Wissenschaft

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "science" in contexts related to science fiction.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @vahramatayan

    science

    np_max-act-logits · claude-4-5-haikuTriggered by @vahramatayan
    New Auto-Interp
    Negative Logits
     logics
    0.47
    f
    0.46
     kere
    0.46
    chargez
    0.44
    <0x0D>
    0.43
     credence
    0.42
     BoxLayout
    0.41
     Dimensions
    0.41
    א
    0.41
    ﻑ
    0.41
    POSITIVE LOGITS
    Theorem
    0.52
     Tabel
    0.51
     angulis
    0.50
     அற்புதமான
    0.48
    Tabla
    0.48
    HIV
    0.47
    특별
    0.47
     rượu
    0.46
    俅
    0.46
    μένο
    0.45
    Act Density 0.014%

    No Known Activations