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

    Neuronpedia

    INDEX
    Explanations

    le

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     casino
    -0.09
    ais
    -0.08
    ário
    -0.08
    aa
    -0.08
     Juan
    -0.08
    far
    -0.07
    ás
    -0.07
     causal
    -0.07
     Gas
    -0.07
    ас
    -0.07
    POSITIVE LOGITS
     delle
    0.11
    LE
    0.08
     le
    0.08
     Le
    0.07
     الل
    0.07
    ICLE
    0.07
     Ple
    0.07
    -le
    0.07
     delicate
    0.07
     две
    0.07
    Act Density 0.015%

    No Known Activations