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

    Neuronpedia

    INDEX
    Explanations

    XML declaration tags in code snippets

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

    start of code or markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oneofs
    -0.60
    providedIn
    -0.52
     الرياضيه
    -0.50
     Ofrece
    -0.47
    unicaciones
    -0.46
     conservación
    -0.44
     conmigo
    -0.43
    abstractmethod
    -0.42
    ffilm
    -0.40
     organización
    -0.40
    POSITIVE LOGITS
    <?
    1.34
     <?
    1.07
     "<?
    0.98
     '<?
    0.96
    ="<?
    0.94
    <?
    0.87
    <?
    0.85
    ><?
    0.72
    "><?
    0.72
    =<?
    0.64
    Act Density 0.009%

    No Known Activations