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

    Neuronpedia

    INDEX
    Explanations

    virtual and accelerating concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Clear
    0.42
    clear
    0.41
    school
    0.41
    optimal
    0.40
    inte
    0.35
    公
    0.35
    test
    0.35
    inum
    0.35
     صنا
    0.35
     immense
    0.35
    POSITIVE LOGITS
     ambition
    0.47
     rých
    0.46
     snelheid
    0.44
     arquivos
    0.43
     unbedingt
    0.42
     аласыз
    0.42
     ambitions
    0.41
     MCT
    0.41
     marshal
    0.41
     aplicativos
    0.41
    Act Density 0.008%

    No Known Activations