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

    Neuronpedia

    INDEX
    Explanations

    Computer screens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (TM
    -0.08
     Chambers
    -0.07
     Concurrent
    -0.07
    amaha
    -0.07
     Bea
    -0.07
     belt
    -0.07
     โ
    -0.07
     Mills
    -0.07
    lea
    -0.06
    743
    -0.06
    POSITIVE LOGITS
    stateParams
    0.07
    <Event
    0.06
    ML
    0.06
     profits
    0.06
    ml
    0.06
    ğimiz
    0.06
     sle
    0.06
    "};↵↵
    0.06
     goddess
    0.06
    ників
    0.05
    Act Density 0.012%

    No Known Activations