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

    Neuronpedia

    INDEX
    Explanations

    goblin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ё
    -0.07
    c
    -0.07
    Sa
    -0.06
    either
    -0.06
    #----------------------------------------------------------------
    -0.06
    orque
    -0.06
    :%
    -0.06
     torso
    -0.06
     upwards
    -0.06
    	icon
    -0.06
    POSITIVE LOGITS
     Goblin
    0.14
    oblins
    0.11
    oblin
    0.10
    カル
    0.08
     реб
    0.07
     Rubin
    0.07
    Elf
    0.07
     PodsDummy
    0.07
     Venezuelan
    0.07
    BIN
    0.06
    Act Density 0.001%

    No Known Activations