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

    Neuronpedia

    INDEX
    Explanations

    Numbers in the nineties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zombie
    -0.08
    Sans
    -0.08
    Royal
    -0.07
     naming
    -0.07
    ombie
    -0.07
    umer
    -0.07
    	element
    -0.07
    629
    -0.07
     sans
    -0.07
     Zombie
    -0.07
    POSITIVE LOGITS
    95
    0.08
    97
    0.08
    94
    0.08
     Tau
    0.08
    98
    0.08
    96
    0.08
    93
    0.07
     sağlamak
    0.07
    097
    0.07
    .UltraWin
    0.07
    Act Density 0.039%

    No Known Activations