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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Leaves
    -0.07
    theorem
    -0.06
     Зам
    -0.06
    
    -0.06
    /static
    -0.06
     XII
    -0.06
    300
    -0.06
    Enterprise
    -0.06
    ('/')
    -0.06
    ратег
    -0.06
    POSITIVE LOGITS
     specification
    0.07
     základní
    0.07
    oriasis
    0.07
     Washing
    0.07
    _meas
    0.06
    uable
    0.06
     трен
    0.06
    .policy
    0.06
    -plane
    0.06
     Του
    0.06
    Act Density 0.016%

    No Known Activations