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

    Neuronpedia

    INDEX
    Explanations

    actions being taken to help animals or objects regarding animals

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    رخ
    -0.07
     duck
    -0.06
     torpedo
    -0.06
    mlin
    -0.06
     significant
    -0.06
    055
    -0.06
     pig
    -0.06
     Cle
    -0.06
     phantom
    -0.06
    é»ĺ
    -0.06
    POSITIVE LOGITS
     capture
    0.14
     captures
    0.13
     Capture
    0.13
    æįķ
    0.12
     traps
    0.11
     trap
    0.11
    capture
    0.11
    captures
    0.10
     catch
    0.10
    Capture
    0.10
    Act Density 0.031%

    No Known Activations