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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating action, capability, or potential outcomes

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

    can be made

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Subscribe
    -0.38
     compagnia
    -0.37
     mété
    -0.36
     hediye
    -0.35
     szolg
    -0.35
    bildēt
    -0.35
     prieš
    -0.35
     zákaz
    -0.35
     piernas
    -0.35
     colazione
    -0.35
    POSITIVE LOGITS
    دانشنامهٔ
    0.56
     JpaRepository
    0.54
    __*/
    0.54
    jstor
    0.52
    RepeatedField
    0.51
     useAppContext
    0.51
    endpush
    0.49
    SaveChangesAsync
    0.49
    RegressionTest
    0.49
    artifactId
    0.48
    Act Density 0.273%

    No Known Activations