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

    Neuronpedia

    INDEX
    Explanations

    provided

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тверд
    -0.08
     grain
    -0.07
    -Star
    -0.06
     Liquid
    -0.06
     kinetics
    -0.06
    ects
    -0.06
    -suite
    -0.06
    asting
    -0.06
     how
    -0.06
    Hen
    -0.06
    POSITIVE LOGITS
     bölg
    0.07
    čení
    0.07
    .overlay
    0.07
    akens
    0.07
     membuat
    0.07
    ↵↵
    0.07
    ��이지
    0.07
    폴
    0.07
     gratuitement
    0.07
     Merkezi
    0.07
    Act Density 0.013%

    No Known Activations