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

    Neuronpedia

    INDEX
    Explanations

    core calculation strength

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UTHERN
    0.55
    سباب
    0.55
     作業
    0.48
     overwrite
    0.47
    rlen
    0.47
    CCOCC
    0.45
    rades
    0.45
    ទ្
    0.45
    ernsey
    0.45
    厩
    0.45
    POSITIVE LOGITS
    ні
    0.59
    。
    0.55
    дні
    0.49
    ită
    0.49
    ді
    0.47
     cidade
    0.46
     domanda
    0.45
     городской
    0.44
    кла
    0.44
    isé
    0.44
    Act Density 0.003%

    No Known Activations