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

    Neuronpedia

    INDEX
    Explanations

    member

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myself
    -0.06
    ey
    -0.06
    inar
    -0.06
    ths
    -0.06
    :string
    -0.06
     Tribunal
    -0.06
    .',
↵
    -0.06
    _hd
    -0.06
     Terms
    -0.06
     Franklin
    -0.06
    POSITIVE LOGITS
     khuôn
    0.07
    ाग
    0.07
     боку
    0.07
     який
    0.07
     цієї
    0.07
     خویش
    0.06
    	elseif
    0.06
     Ви
    0.06
    ";}↵
    0.06
    Began
    0.06
    Act Density 0.004%

    No Known Activations