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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and their associated outcomes

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

    measuring, once, not, is, on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.55
    principalTable
    -0.54
    TargetException
    -0.53
    новништво
    -0.53
    VYMaps
    -0.52
     autorytatywna
    -0.52
    Чыганаклар
    -0.50
     aérienne
    -0.50
     BoxFit
    -0.49
    hésite
    -0.48
    POSITIVE LOGITS
    NUMX
    0.48
     ")");
    0.46
    *);
    0.44
     If
    0.43
    %">
    0.40
     DO
    0.40
     ?>">
    0.39
    })(\
    0.38
    \}=\
    0.38
    >");
    0.38
    Act Density 0.203%

    No Known Activations