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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _joint
    -0.07
    Loaded
    -0.06
    _sent
    -0.06
    _GRAPH
    -0.06
    PCA
    -0.06
     redistrib
    -0.06
     огранич
    -0.06
    Distribution
    -0.06
    ائ
    -0.06
     اختیار
    -0.06
    POSITIVE LOGITS
     Grammar
    0.06
    циклопед
    0.06
    amburger
    0.06
     overposting
    0.06
     euler
    0.06
     perseverance
    0.06
     şirket
    0.06
    early
    0.06
     eds
    0.06
    istory
    0.06
    Act Density 0.008%

    No Known Activations