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

    Neuronpedia

    INDEX
    Explanations

    connecting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    دار
    -0.07
     regimen
    -0.07
     tz
    -0.07
    伦
    -0.07
    369
    -0.06
    =v
    -0.06
    cw
    -0.06
     мала
    -0.06
    씩
    -0.06
    eza
    -0.06
    POSITIVE LOGITS
    ocking
    0.07
     combine
    0.07
     зак
    0.06
    alie
    0.06
     TextField
    0.06
    rients
    0.06
     merge
    0.06
    22
    0.06
    (OP
    0.06
     Dresden
    0.06
    Act Density 0.054%

    No Known Activations