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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     magnets
    0.27
     DJ
    0.25
     rockets
    0.25
    0.25
    OWL
    0.24
    IMATE
    0.24
     a
    0.24
     Tregs
    0.24
     volume
    0.24
     τ
    0.23
    POSITIVE LOGITS
    தற்காக
    0.31
    <0x95>
    0.29
    После
    0.27
    E
    0.27
    <0x8F>
    0.26
    ব্রত
    0.26
    Quando
    0.26
    <0x80>
    0.26
     welchen
    0.25
    Ketika
    0.25
    Act Density 0.025%

    No Known Activations