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

    Neuronpedia

    INDEX
    Explanations

    indicative verbs that suggest a state or action

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

    explaining relationship or consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.46
     gallbladder
    -0.46
    spesies
    -0.44
    footed
    -0.44
     dividers
    -0.44
     Snoop
    -0.44
    
    -0.43
    RegressionTest
    -0.43
     rabb
    -0.43
    KURZBESCHREIBUNG
    -0.43
    POSITIVE LOGITS
     contrary
    0.58
     especially
    0.57
     particularly
    0.56
     evidenced
    0.53
     evident
    0.51
     is
    0.50
     despite
    0.50
     szczególnie
    0.49
     also
    0.49
    Παραπομπές
    0.48
    Act Density 0.041%

    No Known Activations