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

    Neuronpedia

    INDEX
    Explanations

    выбор

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ürnberg
    -0.07
     Brennan
    -0.06
    	bt
    -0.06
     kterým
    -0.06
     менее
    -0.06
     faint
    -0.06
    lém
    -0.06
     staunch
    -0.06
     red
    -0.06
     INLINE
    -0.06
    POSITIVE LOGITS
     利
    0.07
    onya
    0.07
    odial
    0.07
    .health
    0.07
     arsenal
    0.07
    ancements
    0.06
    牙
    0.06
    �
    0.06
     gastro
    0.06
     خود
    0.06
    Act Density 0.002%

    No Known Activations