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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     말이
    -0.06
    enuity
    -0.06
     Workout
    -0.06
    Truthy
    -0.06
     fulfilled
    -0.06
    krvldkf
    -0.06
    ahren
    -0.06
     Behaviour
    -0.06
    lerini
    -0.06
    POSITIVE LOGITS
    .try
    0.07
     कथ
    0.06
    entityManager
    0.06
    _get
    0.06
    ifle
    0.06
    .WinForms
    0.06
     kas
    0.06
     YAML
    0.06
     delimiter
    0.06
    ce
    0.06
    Act Density 0.015%

    No Known Activations