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

    Neuronpedia

    INDEX
    Explanations

    Questions / code inquiries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lí
    -0.10
    养老金
    -0.08
     Automatic
    -0.08
     Selected
    -0.07
     Vampire
    -0.07
     MOST
    -0.07
    -only
    -0.07
     motel
    -0.07
    :")↵
    -0.07
    .selected
    -0.07
    POSITIVE LOGITS
    712
    0.08
     ся
    0.08
     divisions
    0.08
     refer
    0.08
    jast
    0.07
     opet
    0.07
     assembly
    0.07
     sche
    0.07
    ศ
    0.07
     aka
    0.07
    Act Density 0.000%

    No Known Activations