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

    Neuronpedia

    INDEX
    Explanations

    </

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	child
    -0.07
     phong
    -0.06
    раст
    -0.06
    ミ
    -0.06
     condemned
    -0.06
     volte
    -0.06
    ussen
    -0.06
     Mou
    -0.06
     initialise
    -0.06
    imate
    -0.06
    POSITIVE LOGITS
     [<
    0.07
     rs
    0.06
    </
    0.06
    خ
    0.06
     ("<
    0.06
     //----------------
    0.06
     [/
    0.06
    े
    0.06
    .UR
    0.06
    @[
    0.06
    Act Density 0.015%

    No Known Activations