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

    Neuronpedia

    INDEX
    Explanations

    calculus derivatives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dening
    -0.08
     посредством
    -0.08
    議
    -0.08
     untuk
    -0.08
     koriste
    -0.08
    jim
    -0.08
    joy
    -0.08
     güz
    -0.08
    -0.07
     kroz
    -0.07
    POSITIVE LOGITS
     mouth
    0.07
     maintains
    0.07
    .Children
    0.07
    abéns
    0.07
     retains
    0.07
     India's
    0.07
    工作的
    0.07
    .mainloop
    0.06
    ktober
    0.06
      
↵
    0.06
    Act Density 0.022%
    No Known Activations