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

    Neuronpedia

    INDEX
    Explanations

    Code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cancelled
    -0.09
     яны
    -0.08
    ця
    -0.08
     эт
    -0.08
    heg
    -0.08
    цію
    -0.08
     причины
    -0.08
     sollen
    -0.08
     disposition
    -0.08
    abs
    -0.07
    POSITIVE LOGITS
     manually
    0.14
    manual
    0.13
    .manual
    0.12
    Manual
    0.12
     manual
    0.12
     Manual
    0.11
    _manual
    0.11
     manuel
    0.11
     напрямую
    0.10
     DIY
    0.10
    Act Density 0.140%

    No Known Activations