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

    Neuronpedia

    INDEX
    Explanations

    references to specific reports or technical documents

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

    Email subjects

    np_acts-logits-general · gemini-2.0-flash

    Subject: followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SizeF
    -0.49
     Veen
    -0.47
     auparavant
    -0.47
     løs
    -0.46
    anganese
    -0.45
    okolade
    -0.45
     AdapterView
    -0.45
    JKLM
    -0.44
    getch
    -0.44
     Lerner
    -0.43
    POSITIVE LOGITS
     subject
    1.77
    Subject
    1.73
     Subject
    1.71
    subject
    1.65
     SUBJECT
    1.54
    SUBJECT
    1.52
     subjects
    1.43
     subj
    1.20
     Subjects
    1.19
    subjects
    1.18
    Act Density 0.219%

    No Known Activations