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

    Neuronpedia

    INDEX
    Explanations

    the word "somewhere", and sometimes words near it, indicating it might be looking for the general idea of location

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ÑĮв
    -0.07
    soever
    -0.07
    alez
    -0.07
    iasi
    -0.06
    imore
    -0.06
    emic
    -0.06
     Herb
    -0.06
    asher
    -0.06
    lyn
    -0.06
    amine
    -0.06
    POSITIVE LOGITS
     else
    0.12
    _else
    0.08
    else
    0.08
    abouts
    0.07
    Else
    0.07
     Else
    0.07
    fo
    0.07
    aman
    0.07
    UG
    0.07
    280
    0.06
    Act Density 0.028%

    No Known Activations