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

    Neuronpedia

    INDEX
    Explanations

    a mix of uncommon substrings

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.09
    _TYPED
    -0.07
    apg
    -0.06
     vej
    -0.06
    arest
    -0.06
     ?>&
    -0.06
    akukan
    -0.06
    Hp
    -0.06
    kbd
    -0.06
    egment
    -0.06
    POSITIVE LOGITS
    /Q
    0.10
    /q
    0.08
    .Qu
    0.07
    rangle
    0.07
    /qu
    0.06
    δή
    0.06
    ixmap
    0.06
    añ
    0.06
     lsp
    0.06
    atype
    0.06
    Act Density 0.029%

    No Known Activations