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

    Neuronpedia

    INDEX
    Explanations

    ap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，而
    -0.06
    brit
    -0.06
     beacon
    -0.06
    賢
    -0.06
    ีพ
    -0.06
    .Gen
    -0.06
    issional
    -0.06
     ingredients
    -0.06
    TextStyle
    -0.06
    Behind
    -0.06
    POSITIVE LOGITS
    (inputs
    0.07
     Transit
    0.07
    ControlEvents
    0.07
    ава
    0.07
     개
    0.06
     Mud
    0.06
     ↵        ↵
    0.06
    iteration
    0.06
     prio
    0.06
     North
    0.06
    Act Density 0.000%

    No Known Activations