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

    Neuronpedia

    INDEX
    Explanations

    sequences of nested structures or groups, likely related to mathematical or programming contexts

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

    mathematical expressions inside `\left(` and `\right)`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fourrure
    -0.37
    够
    -0.34
     isn
    -0.33
    dAtA
    -0.33
     Dusche
    -0.33
    ствий
    -0.31
    xampp
    -0.31
    蚪
    -0.31
    InitStruct
    -0.30
     oraciones
    -0.29
    POSITIVE LOGITS
     autorytatywna
    0.61
    tvguidetime
    0.56
     transfieras
    0.56
    Weiterlesen
    0.53
    पया
    0.53
    KommentareTeilen
    0.52
    __(/*!
    0.52
    Caro
    0.52
    /***/
    0.51
    estic
    0.49
    Act Density 0.067%

    No Known Activations