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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ese
    -0.07
    resizing
    -0.07
    ัวหน
    -0.06
    латы
    -0.06
     rock
    -0.06
    績
    -0.06
    ')}↵
    -0.06
    Nation
    -0.06
     }}
↵
    -0.06
    ])**
    -0.06
    POSITIVE LOGITS
    (js
    0.07
     WG
    0.07
    UID
    0.07
     APPRO
    0.07
     Louis
    0.07
    延
    0.06
     GOODMAN
    0.06
    filepath
    0.06
     připoj
    0.06
    Clickable
    0.06
    Act Density 0.010%

    No Known Activations