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

    Neuronpedia

    INDEX
    Explanations

    plan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ixel
    -0.07
     系
    -0.07
    -large
    -0.06
     usher
    -0.06
    usty
    -0.06
    getattr
    -0.06
     penal
    -0.06
     hasil
    -0.06
    >\
    -0.06
    -type
    -0.06
    POSITIVE LOGITS
    هنگ
    0.06
     terminating
    0.06
    Guardar
    0.06
    管
    0.06
    .env
    0.06
     looming
    0.06
    ARN
    0.06
    وان
    0.06
    랑
    0.06
     prism
    0.06
    Act Density 0.002%

    No Known Activations