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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns or sequences, particularly focusing on high values

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

    numbers followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    providedIn
    -0.54
    haikusbot
    -0.47
     courriel
    -0.46
    Koordinaten
    -0.45
    WebControls
    -0.45
     endforeach
    -0.44
    RegressionTest
    -0.44
    hikariConfig
    -0.43
     oeil
    -0.43
     pemerintahan
    -0.42
    POSITIVE LOGITS
     XXVIII
    0.62
    춤
    0.55
     CSM
    0.54
     Donato
    0.54
     Artem
    0.53
    nud
    0.52
     Tasmanian
    0.52
     Mateo
    0.52
     CN
    0.52
     Vast
    0.51
    Act Density 0.183%

    No Known Activations