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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .logo
    -0.06
    шу
    -0.06
     pathways
    -0.06
    alignment
    -0.06
    Projectile
    -0.06
     timer
    -0.06
    qrst
    -0.06
     mongoose
    -0.05
     PPP
    -0.05
     род
    -0.05
    POSITIVE LOGITS
     То
    0.07
    دهم
    0.07
    uset
    0.07
    encias
    0.07
     Funeral
    0.06
    حث
    0.06
     「
    0.06
    nímu
    0.06
     arasında
    0.06
    ,g
    0.06
    Act Density 0.083%

    No Known Activations