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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     플
    -0.07
     letz
    -0.06
     n
    -0.06
     меч
    -0.06
    -Bold
    -0.06
     espresso
    -0.06
     k
    -0.06
    Alignment
    -0.06
    缘
    -0.06
     Feld
    -0.06
    POSITIVE LOGITS
    inosaur
    0.06
     freed
    0.06
     primary
    0.06
     alerts
    0.06
     attained
    0.06
     ROLE
    0.06
     भर
    0.06
    booking
    0.06
    Remaining
    0.06
     addslashes
    0.06
    Act Density 0.001%

    No Known Activations