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

    Neuronpedia

    INDEX
    Explanations

    hug

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (move
    -0.07
     Threshold
    -0.07
     shifts
    -0.07
     Latitude
    -0.07
    RenderWindow
    -0.07
    	open
    -0.07
     resistance
    -0.07
     spectrum
    -0.07
     trajectories
    -0.06
     стану
    -0.06
    POSITIVE LOGITS
     hug
    0.09
     hugs
    0.08
     hugged
    0.08
    (InputStream
    0.06
    ηγ
    0.06
     grabbed
    0.06
     kissing
    0.06
     kiss
    0.06
     writeFile
    0.06
     Italian
    0.06
    Act Density 0.014%

    No Known Activations