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

    Neuronpedia

    INDEX
    Explanations

    math and problem solving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hitt
    -0.10
     трудно
    -0.09
     настолько
    -0.08
     вовсе
    -0.08
    jf
    -0.08
     достаточно
    -0.08
     strangely
    -0.08
     מס
    -0.08
     уни
    -0.08
     näytt
    -0.08
    POSITIVE LOGITS
     classic
    0.12
     typical
    0.10
     typically
    0.10
    经典
    0.10
    通常
    0.10
    典
    0.10
     commonly
    0.10
     Typically
    0.09
    Typical
    0.09
     klasik
    0.09
    Act Density 0.211%

    No Known Activations