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

    Neuronpedia

    INDEX
    Explanations

    Python code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     simply
    0.42
    decl
    0.39
    Persistent
    0.39
     irreparable
    0.36
     similares
    0.36
    α
    0.36
    at
    0.35
    новой
    0.35
     esto
    0.35
     arms
    0.35
    POSITIVE LOGITS
     commemorate
    0.44
    शेखर
    0.43
     относя
    0.41
    深的
    0.41
    ANGMAR
    0.39
     जगा
    0.39
     बिटकॉइन
    0.38
    IntVar
    0.38
     VCO
    0.38
     CAGR
    0.37
    Act Density 0.000%

    No Known Activations