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
     projector
    -0.07
    resize
    -0.06
     tumors
    -0.06
    ssf
    -0.06
     hubs
    -0.06
    ’Brien
    -0.06
    reader
    -0.06
     Springs
    -0.06
     Habitat
    -0.06
     Düz
    -0.06
    POSITIVE LOGITS
    .Enc
    0.07
    ...↵
    0.06
    ogr
    0.06
     RECE
    0.06
    	Y
    0.06
    achie
    0.06
    """
↵
↵
    0.06
    ...↵
    0.06
     Cần
    0.06
     predecess
    0.06
    Act Density 0.011%

    No Known Activations