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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    してい
    -0.07
    西省
    -0.06
    	Port
    -0.06
     refute
    -0.06
    stop
    -0.06
     quien
    -0.06
    �
    -0.06
    .Identifier
    -0.06
    bolt
    -0.05
     Civ
    -0.05
    POSITIVE LOGITS
     extends
    0.07
    θρώ
    0.07
    ila
    0.07
    <img
    0.06
    यह
    0.06
    metatable
    0.06
     signage
    0.06
    IM
    0.06
     tensions
    0.06
    each
    0.06
    Act Density 0.000%

    No Known Activations