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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical expressions and programming structures

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

    date parent exam

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mouthed
    -0.60
     Ret
    -0.55
     Gund
    -0.55
    ized
    -0.54
     RET
    -0.54
    secuted
    -0.54
     Laura
    -0.53
     εύ
    -0.53
    fighting
    -0.53
    iomanip
    -0.53
    POSITIVE LOGITS
     CascadeType
    0.44
     ostavi
    0.34
    AndEndTag
    0.33
    DIPSETTING
    0.33
    criminator
    0.31
    FailureListener
    0.30
     архивлан
    0.30
    +:+
    0.30
     beiden
    0.29
    +#+#
    0.29
    Act Density 0.594%

    No Known Activations