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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hacked
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
     dij
    -0.06
     sĩ
    -0.06
     atleast
    -0.06
    maxlength
    -0.06
    ीआई
    -0.06
    _click
    -0.06
    iversary
    -0.06
    нице
    -0.06
    POSITIVE LOGITS
    -present
    0.08
     depths
    0.07
    [now
    0.06
    *↵
    0.06
    ۶
    0.06
     expenditures
    0.06
    フ
    0.06
     �
    0.06
    .people
    0.06
    (vertical
    0.06
    Act Density 0.000%

    No Known Activations