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

    Neuronpedia

    INDEX
    Explanations

    expressions and constructs related to modal verbs and their usage

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

    confirmation questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elkaar
    -0.51
     it
    -0.47
     them
    -0.44
     frontières
    -0.44
    zelfde
    -0.44
     siinä
    -0.43
    ponses
    -0.43
     Exacts
    -0.42
    einander
    -0.42
     это
    -0.41
    POSITIVE LOGITS
     still
    0.59
     again
    0.56
    LookAnd
    0.54
     only
    0.54
     always
    0.53
    OGND
    0.52
     wieder
    0.51
    again
    0.47
     weer
    0.47
    still
    0.47
    Act Density 0.005%

    No Known Activations