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

    Neuronpedia

    INDEX
    Explanations

    conservative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ٤
    -0.07
    	st
    -0.07
    след
    -0.06
    -я
    -0.06
     �
    -0.06
     RECORD
    -0.06
     её
    -0.06
    IMATE
    -0.06
    .attrs
    -0.06
     المش
    -0.06
    POSITIVE LOGITS
    甚至
    0.07
     dáv
    0.06
     triang
    0.06
    addir
    0.06
    lesi
    0.06
     воспал
    0.06
     goat
    0.06
     comply
    0.06
     delete
    0.06
    observeOn
    0.06
    Act Density 0.003%

    No Known Activations