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

    Neuronpedia

    INDEX
    Explanations

    statements indicating functionality and satisfaction with results

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

    everything is functioning or described

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.60
     surla
    -0.59
     referrerpolicy
    -0.59
    Tē
    -0.54
    лтамалар
    -0.54
    whole
    -0.54
     ganze
    -0.54
     informée
    -0.52
    entire
    -0.52
     الرياضيه
    -0.51
    POSITIVE LOGITS
     including
    0.72
     except
    0.69
     Including
    0.60
     включая
    0.59
    except
    0.59
     excepto
    0.57
     incluyendo
    0.57
    including
    0.57
     EXCEPT
    0.55
    Except
    0.55
    Act Density 0.051%

    No Known Activations