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

    Neuronpedia

    INDEX
    Explanations

    separation/isolation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _COMPLETED
    -0.07
     Male
    -0.07
    _disabled
    -0.07
     cruc
    -0.07
    抛弃
    -0.06
    Place
    -0.06
    样板
    -0.06
    SError
    -0.06
    posables
    -0.06
    ɯ
    -0.06
    POSITIVE LOGITS
    ylation
    0.07
     IRS
    0.07
     amendments
    0.07
    	lib
    0.07
    .peer
    0.06
    ца
    0.06
    踔
    0.06
    <std
    0.06
    cka
    0.06
     Aim
    0.06
    Act Density 0.031%

    No Known Activations