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

    Neuronpedia

    INDEX
    Explanations

    Legal/court context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đúng
    -0.08
    Pressure
    -0.07
     organizations
    -0.07
    adol
    -0.06
    样子
    -0.06
    udeau
    -0.06
    greens
    -0.06
    очные
    -0.06
     zoning
    -0.06
     workstation
    -0.06
    POSITIVE LOGITS
     adını
    0.06
    γρα
    0.06
     fig
    0.06
     смеш
    0.06
     satisf
    0.06
     ovliv
    0.06
     Fig
    0.06
     Zus
    0.06
     周
    0.06
     Rust
    0.06
    Act Density 0.015%

    No Known Activations