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

    Neuronpedia

    INDEX
    Explanations

    planning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yön
    -0.07
    duck
    -0.06
    elfast
    -0.06
     enrichment
    -0.06
    etection
    -0.06
     Assets
    -0.06
    thumbnail
    -0.06
     dày
    -0.06
    conv
    -0.06
    екси
    -0.06
    POSITIVE LOGITS
    щими
    0.07
    -min
    0.07
    -us
    0.07
     RELATED
    0.07
     incidents
    0.06
     minim
    0.06
    _ped
    0.06
    ighter
    0.06
     canned
    0.06
     miser
    0.06
    Act Density 0.003%

    No Known Activations