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

    Neuronpedia

    INDEX
    Explanations

    future events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ccording
    -0.06
    лися
    -0.06
    /ca
    -0.06
    irus
    -0.06
     bloginfo
    -0.06
    (condition
    -0.06
    Metal
    -0.06
    rze
    -0.05
     Surface
    -0.05
     cmdline
    -0.05
    POSITIVE LOGITS
     の
    0.08
     Un
    0.07
     lawful
    0.07
    額
    0.07
     neighbour
    0.06
     Fahr
    0.06
    ilen
    0.06
    Un
    0.06
    额
    0.06
    tain
    0.06
    Act Density 0.011%

    No Known Activations