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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bếp
    -0.07
     客
    -0.06
    /network
    -0.06
     corridors
    -0.06
    .Txt
    -0.06
    erral
    -0.06
    .Vertical
    -0.06
    isify
    -0.06
    模式
    -0.06
    .managed
    -0.06
    POSITIVE LOGITS
     defamation
    0.07
     Hungarian
    0.07
     affection
    0.06
    ections
    0.06
     distinct
    0.06
    "f
    0.06
     unrelated
    0.06
     stable
    0.06
     Ts
    0.06
     Belmont
    0.06
    Act Density 0.015%

    No Known Activations