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

    Neuronpedia

    INDEX
    Explanations

    say [metal names]

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plywood
    -0.06
    \Repository
    -0.06
     رضا
    -0.06
    wise
    -0.06
     Suddenly
    -0.06
    :-
    -0.06
    edis
    -0.06
     folders
    -0.06
     thicker
    -0.06
     shocks
    -0.06
    POSITIVE LOGITS
     plentiful
    0.07
    (State
    0.07
     lze
    0.06
     действия
    0.06
     đu
    0.06
    '↵
    0.06
    -response
    0.06
    uche
    0.06
    ="<?
    0.06
     espera
    0.06
    Act Density 0.016%

    No Known Activations