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

    Neuronpedia

    INDEX
    Explanations

    statements regarding statistical observations or events

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

    first attempt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DeleteBehavior
    -0.53
    Derbyniad
    -0.52
     ostavi
    -0.49
    发表于
    -0.49
    ItemBackground
    -0.48
     Numerade
    -0.47
    HasForeignKey
    -0.46
     protoimpl
    -0.45
    الإنجليزية
    -0.45
    formik
    -0.44
    POSITIVE LOGITS
     defensive
    0.36
    gliere
    0.36
     MainAxisSize
    0.36
     withdrawn
    0.35
    ɵɵelementStart
    0.35
    MENAFN
    0.34
     لينك
    0.34
     commanded
    0.33
    lindung
    0.33
     limitation
    0.33
    Act Density 0.122%

    No Known Activations