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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blister
    -0.07
     Dry
    -0.07
    ágenes
    -0.07
     handlers
    -0.07
     Jewish
    -0.07
    itler
    -0.07
    ойчив
    -0.06
    ský
    -0.06
     American
    -0.06
     remedy
    -0.06
    POSITIVE LOGITS
     each
    0.14
     Each
    0.11
     EACH
    0.09
    Each
    0.09
     NEC
    0.07
     cada
    0.07
    xac
    0.06
     Contest
    0.06
    each
    0.06
    leine
    0.06
    Act Density 0.061%

    No Known Activations