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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Під
    -0.07
     repmat
    -0.06
     volcan
    -0.06
    jvu
    -0.06
     doğrudan
    -0.06
    uropean
    -0.05
     شماره
    -0.05
    .Observable
    -0.05
    よね
    -0.05
    거리
    -0.05
    POSITIVE LOGITS
    .cont
    0.07
     sentinel
    0.06
    افع
    0.06
    رح
    0.06
    ocker
    0.06
     arising
    0.06
    lover
    0.06
     я
    0.06
    130
    0.06
     destination
    0.06
    Act Density 0.608%

    No Known Activations