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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical and data processing concepts

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

    code parsing and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sch
    -0.32
    従
    -0.29
     Res
    -0.26
     Plan
    -0.26
     capture
    -0.25
     mé
    -0.25
     Fu
    -0.24
    理
    -0.24
     Bog
    -0.24
     fis
    -0.23
    POSITIVE LOGITS
     ब्रेकडाउन
    0.91
    SequentialGroup
    0.85
     Administrativna
    0.84
    expandindo
    0.81
     autorytatywna
    0.77
    SharedDtor
    0.77
    complexContent
    0.77
    帖最后由
    0.75
    +#+#
    0.75
     noDo
    0.74
    Act Density 0.005%

    No Known Activations