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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    activ
    -0.07
     Amazon
    -0.07
    uccess
    -0.06
    炎
    -0.06
    莎
    -0.06
    <u
    -0.06
     Shotgun
    -0.06
    )){
↵
    -0.06
     listar
    -0.06
     Material
    -0.06
    POSITIVE LOGITS
    (stderr
    0.07
    ักด
    0.07
    cq
    0.07
     anmeld
    0.06
    छ
    0.06
    Candidate
    0.06
    arda
    0.06
    EZ
    0.06
    	override
    0.06
     начале
    0.06
    Act Density 0.073%

    No Known Activations