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

    Neuronpedia

    INDEX
    Explanations

    List manipulation by position

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depicting
    -0.08
     depress
    -0.08
     ____
    -0.07
     الرب
    -0.07
     clim
    -0.07
     Rah
    -0.07
    	glut
    -0.07
     attribution
    -0.07
     spela
    -0.07
     sapphire
    -0.07
    POSITIVE LOGITS
     survivors
    0.11
     surviving
    0.10
     nouvo
    0.09
     zomb
    0.09
     surviv
    0.09
     superviv
    0.09
    nger
    0.09
     Surviv
    0.09
     survive
    0.09
     surv
    0.08
    Act Density 0.009%

    No Known Activations