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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (request
    -0.08
    (GL
    -0.07
     skulle
    -0.07
    (APP
    -0.07
    	yy
    -0.07
     glu
    -0.07
    alfa
    -0.06
     ADVISED
    -0.06
    \Builder
    -0.06
    绿水
    -0.06
    POSITIVE LOGITS
     backups
    0.08
     Widow
    0.08
     ejected
    0.07
    יד
    0.07
    face
    0.07
    _SURFACE
    0.07
    коп
    0.07
    kt
    0.07
    end
    0.07
     Layers
    0.07
    Act Density 0.016%

    No Known Activations