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

    Neuronpedia

    INDEX
    Explanations

    consider size and perhaps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     modulates
    0.41
     austenitic
    0.39
    Works
    0.38
    Weyl
    0.38
     achieves
    0.37
     œuvres
    0.37
     chandeliers
    0.37
     alloys
    0.37
     conducts
    0.37
     produces
    0.36
    POSITIVE LOGITS
     рассматри
    0.35
     considerando
    0.35
     правда
    0.33
     Consid
    0.33
    perhaps
    0.32
     बोली
    0.32
    си
    0.31
     आश्चर्य
    0.30
    dplyr
    0.30
    гда
    0.30
    Act Density 0.000%

    No Known Activations