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

    Neuronpedia

    INDEX
    Explanations

    include/exclude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compound
    -0.07
     BY
    -0.07
    ி
    -0.07
     Benef
    -0.06
    ession
    -0.06
     waiver
    -0.06
     volleyball
    -0.06
    ipment
    -0.06
     implic
    -0.06
    uggest
    -0.06
    POSITIVE LOGITS
    _NON
    0.08
    AutoresizingMask
    0.07
    elijke
    0.07
     :/:
    0.07
    .maven
    0.07
     cuckold
    0.06
    rico
    0.06
     glfw
    0.06
     教
    0.06
     Smile
    0.06
    Act Density 0.028%

    No Known Activations