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

    Neuronpedia

    INDEX
    Explanations

    Filipino words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lif
    0.55
     cré
    0.53
     neurom
    0.52
     Alternatively
    0.50
     neumáticos
    0.50
     openc
    0.50
     optionally
    0.50
     monod
    0.50
     progressively
    0.49
     continual
    0.49
    POSITIVE LOGITS
     kahit
    1.34
     dahil
    1.31
     mga
    1.28
    Mga
    1.27
     isang
    1.26
     hindi
    1.25
     lahat
    1.25
     walang
    1.23
     lamang
    1.21
     iyong
    1.20
    Act Density 0.007%

    No Known Activations