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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating capability or inability to perform actions

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

    able to verbfact that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     telefónica
    -0.43
     táctil
    -0.40
     Worse
    -0.38
    SetString
    -0.38
    Worse
    -0.38
     navideños
    -0.37
    Síguenos
    -0.36
     plateado
    -0.36
    ache
    -0.35
     suffice
    -0.35
    POSITIVE LOGITS
     disambiguazione
    0.72
    findpost
    0.64
     JpaRepository
    0.53
    évaluateur
    0.51
    RegressionTest
    0.51
     iż
    0.50
    ᅠ
    0.49
     MessageBoxIcon
    0.49
    جوايز
    0.47
     arşivlendi
    0.46
    Act Density 0.310%

    No Known Activations