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

    Neuronpedia

    INDEX
    Explanations

    looking through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mikhail
    -0.08
     tử
    -0.07
     Mp
    -0.07
    strate
    -0.07
    -oriented
    -0.06
    (Response
    -0.06
    ial
    -0.06
    .setToolTip
    -0.06
     名
    -0.06
    Ap
    -0.06
    POSITIVE LOGITS
     pouvoir
    0.07
    (handles
    0.06
    thood
    0.06
     keras
    0.06
     guitars
    0.06
     tinha
    0.06
     das
    0.06
    猫
    0.06
    _COLOR
    0.06
    .logging
    0.06
    Act Density 0.020%

    No Known Activations