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

    Neuronpedia

    INDEX
    Explanations

    growth and renewal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     собак
    1.17
     supremo
    1.14
     malaria
    1.10
     WeChat
    1.09
     sped
    1.09
     figli
    1.09
     Mathematik
    1.09
     Fahrzeug
    1.07
     Aufgabe
    1.07
     habitat
    1.06
    POSITIVE LOGITS
    subscriber
    1.13
    esthetics
    1.09
    리
    1.07
    s
    1.02
    glass
    0.98
    no
    0.96
    Init
    0.94
    Expression
    0.93
    bian
    0.93
    μού
    0.92
    Act Density 0.001%

    No Known Activations