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

    Neuronpedia

    INDEX
    Explanations

    na

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gros
    -0.07
    ，同时
    -0.07
    PCM
    -0.06
     extortion
    -0.06
    angepicker
    -0.06
     militant
    -0.06
     murderous
    -0.06
     Foundation
    -0.06
    .rep
    -0.06
    啦
    -0.06
    POSITIVE LOGITS
    ่วย
    0.07
    Create
    0.06
    erves
    0.06
     rhet
    0.06
    Dice
    0.06
    civil
    0.06
    (part
    0.06
     bij
    0.06
    LEAR
    0.06
    Cold
    0.06
    Act Density 0.000%

    No Known Activations