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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chten
    -0.07
    Before
    -0.06
    .Columns
    -0.06
    .sec
    -0.06
    ován
    -0.06
    zí
    -0.06
     dolore
    -0.06
    をする
    -0.06
     thuyết
    -0.06
    AAA
    -0.06
    POSITIVE LOGITS
    _sales
    0.07
    Playable
    0.06
    446
    0.06
    143
    0.06
     pict
    0.06
     curriculum
    0.06
    Stub
    0.06
    (State
    0.06
     republic
    0.06
    (solution
    0.06
    Act Density 0.021%

    No Known Activations