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

    Neuronpedia

    INDEX
    Explanations

    sections related to discussions of rules or guidelines in professional settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Common words at the start of sentences

    np_acts-logits-general · gemini-2.0-flash

    iron limitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mybatisplus
    -0.73
    stdc
    -0.72
     par
    -0.69
    ArgumentParser
    -0.67
     qu
    -0.66
    WAUKEE
    -0.66
     co
    -0.66
    tvguidetime
    -0.66
     dem
    -0.65
     ang
    -0.65
    POSITIVE LOGITS
    The
    1.47
    There
    1.16
     itſelf
    1.15
    This
    1.13
    It
    1.06
     The
    1.06
    When
    1.05
    In
    1.02
    If
    0.99
    While
    0.99
    Act Density 1.161%

    No Known Activations