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

    Neuronpedia

    INDEX
    Explanations

    script

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     no
    -0.07
    Blocking
    -0.06
     replaces
    -0.06
    $sub
    -0.06
    926
    -0.06
    aqu
    -0.06
     зни
    -0.06
    -no
    -0.06
     fenced
    -0.06
    \Type
    -0.06
    POSITIVE LOGITS
    nek
    0.07
     jede
    0.06
    ,np
    0.06
    .DisplayStyle
    0.06
    lems
    0.06
     nurture
    0.06
    atég
    0.06
    肉
    0.06
     Kaepernick
    0.06
    	Runtime
    0.06
    Act Density 0.001%

    No Known Activations