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

    Neuronpedia

    INDEX
    Explanations

    their/your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     попада
    -0.07
    ancybox
    -0.07
     fundraiser
    -0.07
    workspace
    -0.07
     finding
    -0.06
    /hooks
    -0.06
     hơn
    -0.06
    (["
    -0.06
    akov
    -0.06
     salope
    -0.06
    POSITIVE LOGITS
     tsp
    0.07
    ,this
    0.06
     sine
    0.06
    :P
    0.06
    "M
    0.06
     sole
    0.06
    "s
    0.06
    زم
    0.06
     roofing
    0.05
     modifiers
    0.05
    Act Density 0.022%

    No Known Activations