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

    Neuronpedia

    INDEX
    Explanations

    no group photos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ETA
    0.41
     remnant
    0.40
    Carrier
    0.39
    navigation
    0.39
     timing
    0.37
    Certainly
    0.37
     Navarre
    0.37
     authorizations
    0.36
    receiver
    0.36
     kuchen
    0.36
    POSITIVE LOGITS
     überzeugt
    0.45
     ಗು
    0.44
     shocked
    0.44
     usando
    0.43
    最优
    0.43
    震惊
    0.42
     посвя
    0.42
    会上
    0.41
    što
    0.41
     mejorar
    0.41
    Act Density 0.007%

    No Known Activations