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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     traps
    -0.07
    ucas
    -0.07
    Background
    -0.06
     Method
    -0.06
     builder
    -0.06
     doubted
    -0.06
     aura
    -0.06
     UNKNOWN
    -0.06
    $path
    -0.06
    tor
    -0.06
    POSITIVE LOGITS
    美
    0.07
    .Many
    0.06
    разу
    0.06
    rey
    0.06
    ideas
    0.06
    *u
    0.06
    ='<
    0.06
    expert
    0.06
    _gr
    0.06
    activ
    0.06
    Act Density 0.000%

    No Known Activations