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

    Neuronpedia

    INDEX
    Explanations

    prolog, log

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �果
    -0.07
    -switch
    -0.07
    身
    -0.07
    Mult
    -0.07
    Creating
    -0.07
    (indices
    -0.07
     Niagara
    -0.07
     Utility
    -0.06
    工作
    -0.06
     Orthodox
    -0.06
    POSITIVE LOGITS
    ":"","
    0.07
     innate
    0.07
     Rocket
    0.06
     ↓
    0.06
    izzling
    0.06
     fray
    0.06
     verdiği
    0.06
    ritos
    0.06
     decline
    0.06
     इसम
    0.05
    Act Density 0.007%

    No Known Activations