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

    Neuronpedia

    INDEX
    Explanations

    greetings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itself
    -0.07
     woven
    -0.07
    ível
    -0.06
    BindView
    -0.06
    NP
    -0.06
     herself
    -0.06
    cao
    -0.06
     Bien
    -0.06
     grew
    -0.06
     indexing
    -0.06
    POSITIVE LOGITS
     salute
    0.09
     sluts
    0.07
     offset
    0.07
    	speed
    0.07
    uty
    0.07
     aquatic
    0.07
    :;↵
    0.07
    „V
    0.07
     TU
    0.06
    (Camera
    0.06
    Act Density 0.003%

    No Known Activations