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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurements and data in scientific or technical contexts

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

    units, technical terms, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ьаж
    -0.57
    ագրություններ
    -0.54
     noDo
    -0.53
    argout
    -0.53
    OGND
    -0.51
    SourceChecksum
    -0.46
     Normdatei
    -0.43
    dormit
    -0.41
    ########.
    -0.41
    yethylene
    -0.40
    POSITIVE LOGITS
    intios
    0.52
     escuchado
    0.47
    antaranya
    0.47
     classiques
    0.45
     asesinado
    0.44
     itſelf
    0.43
     följande
    0.42
     avoient
    0.42
     ámbitos
    0.41
    InitialState
    0.41
    Act Density 0.081%

    No Known Activations