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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icerca
    -0.08
    Within
    -0.07
     DOE
    -0.07
     concepts
    -0.07
     Federal
    -0.07
    クセ
    -0.07
     NATO
    -0.07
     mensaje
    -0.07
    などの
    -0.07
    .httpClient
    -0.07
    POSITIVE LOGITS
     ())↵
    0.06
     друж
    0.06
    oppel
    0.06
    léd
    0.06
    usb
    0.06
    (push
    0.06
    願
    0.05
    виж
    0.05
    ork
    0.05
     уход
    0.05
    Act Density 0.002%

    No Known Activations