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

    Neuronpedia

    INDEX
    Explanations

    Correctness/Consistency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     popover
    -0.08
    萝
    -0.07
     fats
    -0.07
    Tex
    -0.07
    🦍
    -0.06
     Laf
    -0.06
     gracious
    -0.06
     haar
    -0.06
     violates
    -0.06
    ᔕ
    -0.06
    POSITIVE LOGITS
    酿酒
    0.08
    _USERS
    0.07
     xcb
    0.07
    都已经
    0.07
     cricket
    0.07
    czył
    0.07
     ин
    0.06
    大事
    0.06
    >";
    0.06
    ırl
    0.06
    Act Density 0.020%

    No Known Activations