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

    Neuronpedia

    INDEX
    Explanations

    currency symbols

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

    Mathematical and code-related expressions

    np_acts-logits-general · gemini-2.0-flash

    superscripts and subscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.76
     оригіналу
    -0.69
    Pozdrawiam
    -0.68
     Alves
    -0.60
    AfterClass
    -0.59
    ArrowToggle
    -0.59
    Cordialement
    -0.56
     noDo
    -0.56
    es
    -0.55
    ors
    -0.55
    POSITIVE LOGITS
    |}{$
    0.80
    tvguidetime
    0.76
     Mep
    0.72
    stalline
    0.71
    theless
    0.70
     barbarians
    0.69
     Kof
    0.68
    "]}
    0.68
     constitutions
    0.67
    hibitions
    0.67
    Act Density 0.312%

    No Known Activations