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

    Neuronpedia

    INDEX
    Explanations

    Laser Cut, identity theft, Salesforce ERP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yani
    0.39
    लेकिन
    0.38
    l
    0.36
     l
    0.34
     {
    0.34
     చంద్ర
    0.32
    winged
    0.32
    rotated
    0.32
    Cread
    0.32
    ilize
    0.32
    POSITIVE LOGITS
     समेत
    0.39
    ).\\
    0.39
     وغیرہ
    0.38
    🕓
    0.37
    みを
    0.37
    。」
    0.37
     वगैरह
    0.36
    ơm
    0.36
    matig
    0.36
     тощо
    0.35
    Act Density 0.149%

    No Known Activations