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

    Neuronpedia

    INDEX
    Explanations

    Geographic area

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lure
    -0.07
     seals
    -0.07
     persuasion
    -0.07
     tvoř
    -0.06
    _yaml
    -0.06
    jured
    -0.06
    둘
    -0.06
     airy
    -0.06
     graduated
    -0.06
     Ông
    -0.06
    POSITIVE LOGITS
    _EQUAL
    0.07
     SM
    0.07
     ENV
    0.07
     checker
    0.07
     Famil
    0.06
     eid
    0.06
    $instance
    0.06
     �
    0.06
    _clicked
    0.06
     EG
    0.06
    Act Density 0.017%

    No Known Activations