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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     นาง
    -0.07
    ="+
    -0.07
    ορειο
    -0.07
     costing
    -0.06
     subscribers
    -0.06
     Nine
    -0.06
    	op
    -0.06
    	word
    -0.06
     자유
    -0.06
    POSITIVE LOGITS
    (pwd
    0.07
     from
    0.07
     RETURNS
    0.07
    :::::::::::
    0.07
     dele
    0.06
    acam
    0.06
    (F
    0.06
    retorno
    0.06
     timers
    0.06
     okres
    0.06
    Act Density 0.012%

    No Known Activations