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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     표시
    -0.06
    istung
    -0.06
    きた
    -0.06
    _ALIGNMENT
    -0.06
     ดาว
    -0.06
    ご
    -0.06
    .BASELINE
    -0.06
    밀
    -0.06
    gesture
    -0.06
    _CLIP
    -0.06
    POSITIVE LOGITS
     Benjamin
    0.07
     hl
    0.07
     prophets
    0.07
    Russian
    0.07
     dead
    0.07
     migrate
    0.06
     requis
    0.06
     Reserved
    0.06
    vinfos
    0.06
    leader
    0.06
    Act Density 0.000%

    No Known Activations