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

    Neuronpedia

    INDEX
    Explanations

    say "them"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iv
    -0.08
     Wich
    -0.07
    入库
    -0.07
    _GenericClass
    -0.07
     quits
    -0.07
     Hutchinson
    -0.06
     Oxygen
    -0.06
    _DEAD
    -0.06
    _Static
    -0.06
    歃
    -0.06
    POSITIVE LOGITS
     '/
    0.07
    gl
    0.07
    fill
    0.07
     따라
    0.07
    issue
    0.07
    ]])↵
    0.06
    ตลาด
    0.06
    判处
    0.06
    always
    0.06
    fs
    0.06
    Act Density 0.376%

    No Known Activations