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

    Neuronpedia

    INDEX
    Explanations

    structured code comments or documentation

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

    symbols followed by 'summary' or 'eval'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unless
    -0.36
     Solve
    -0.36
     tab
    -0.34
    Solve
    -0.33
     للاسماء
    -0.32
     Stirn
    -0.32
     fils
    -0.32
     isolate
    -0.32
     Sotto
    -0.31
     fille
    -0.31
    POSITIVE LOGITS
    %%%%%%%%
    1.55
    %%%%%%%%%%%%
    1.54
    %%%
    1.53
    %%%%%%%
    1.47
    %%%%%
    1.47
    %%%%%%%%%
    1.42
    %%%%%%
    1.41
    %%%%%%%%%%
    1.39
    %%%%
    1.34
    %%%%%%%%%%%%%%%%
    0.89
    Act Density 0.008%

    No Known Activations