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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    кових
    -0.07
     HID
    -0.06
     Rigidbody
    -0.06
    _ICON
    -0.06
    .Throw
    -0.06
     unfit
    -0.06
    เฉพาะ
    -0.06
    áč
    -0.06
    asad
    -0.06
     rsa
    -0.06
    POSITIVE LOGITS
    .beh
    0.07
    _bind
    0.06
     too
    0.06
     budgets
    0.06
     council
    0.06
     skinny
    0.06
     leadership
    0.06
    ())),↵
    0.06
     preced
    0.06
     punish
    0.06
    Act Density 0.048%

    No Known Activations