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

    Neuronpedia

    INDEX
    Explanations

    Meats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pension
    -0.06
    cut
    -0.06
     Derived
    -0.06
     ट
    -0.06
     Unit
    -0.06
    ENOMEM
    -0.06
     backed
    -0.06
    стру
    -0.06
    dehyde
    -0.06
     influencers
    -0.06
    POSITIVE LOGITS
    หม
    0.07
    /L
    0.07
    alice
    0.07
    SRC
    0.07
     //=
    0.07
    aisy
    0.06
     truth
    0.06
    SYM
    0.06
     backbone
    0.06
     liste
    0.06
    Act Density 0.027%

    No Known Activations