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

    Neuronpedia

    INDEX
    Explanations

    rock climbing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     borrowed
    -0.07
    uniform
    -0.07
    �от
    -0.06
     activate
    -0.06
    мами
    -0.06
    _aff
    -0.06
     Against
    -0.06
     Rick
    -0.06
     reprodu
    -0.06
    άλυψης
    -0.06
    POSITIVE LOGITS
    ?“↵↵
    0.07
    (MSG
    0.07
     tert
    0.06
    背景
    0.06
    ="";
↵
    0.06
    ouncil
    0.06
    >.↵
    0.06
     archetype
    0.06
    委员会
    0.06
    ývá
    0.06
    Act Density 0.074%

    No Known Activations