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

    Neuronpedia

    INDEX
    Explanations

    detailed descriptions of car features and conditions

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

    user prompts before responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    开心
    -0.28
     program
    -0.28
     espoir
    -0.28
     teacher
    -0.28
    és
    -0.27
     déclarations
    -0.25
     qualifi
    -0.25
     inade
    -0.24
    =[];
    -0.24
     metodología
    -0.24
    POSITIVE LOGITS
    AnchorStyles
    0.68
     AssemblyCulture
    0.65
     ExecuteAsync
    0.64
    RTLI
    0.63
    lowers
    0.62
    platinum
    0.62
    DockStyle
    0.61
    MigrationBuilder
    0.61
    cosmetic
    0.60
     OMITBAD
    0.60
    Act Density 0.012%

    No Known Activations