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

    Neuronpedia

    INDEX
    Explanations

    tamarind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    floor
    0.48
    Floor
    0.40
     Floor
    0.39
    quali
    0.39
    mington
    0.38
    atori
    0.38
    pering
    0.37
     floor
    0.36
    soon
    0.36
    typename
    0.35
    POSITIVE LOGITS
     Tamar
    0.45
    indo
    0.44
    んだ
    0.41
    ack
    0.40
    ौड़
    0.39
    ickej
    0.38
     neutralized
    0.37
    ╠
    0.37
    皁
    0.37
     Biraz
    0.37
    Act Density 0.002%

    No Known Activations