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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PQ
    -0.08
    -leaning
    -0.07
     xd
    -0.07
     Nest
    -0.07
    BOOST
    -0.07
    _plane
    -0.07
    oric
    -0.07
    partial
    -0.07
    -sex
    -0.07
     nest
    -0.06
    POSITIVE LOGITS
     //~
    0.06
     гара
    0.06
    dia
    0.06
     Cri
    0.06
    /)↵
    0.06
    adiens
    0.05
     stumbling
    0.05
     flowers
    0.05
    нюю
    0.05
     亚洲
    0.05
    Act Density 0.038%

    No Known Activations