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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     такий
    -0.06
    alnum
    -0.06
     Elvis
    -0.06
    .Evaluate
    -0.06
    Uid
    -0.06
    ολ
    -0.06
     Some
    -0.06
    zenia
    -0.06
     enormously
    -0.06
    ışık
    -0.06
    POSITIVE LOGITS
    	intent
    0.07
     içine
    0.07
    (file
    0.06
    ({↵
    0.06
    603
    0.06
     bite
    0.06
     posters
    0.06
    728
    0.06
     intensive
    0.06
     Blazers
    0.06
    Act Density 0.000%

    No Known Activations