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
    .lift
    -0.07
     přesně
    -0.07
     Reggie
    -0.07
     робота
    -0.06
     graphene
    -0.06
     قابل
    -0.06
    оти
    -0.06
     sweeps
    -0.06
     archetype
    -0.06
    سازی
    -0.06
    POSITIVE LOGITS
     School
    0.07
    Left
    0.06
    _qu
    0.06
    (&:
    0.06
     거
    0.06
     Institution
    0.06
     {},
    0.06
     Left
    0.06
     xứ
    0.06
     futures
    0.06
    Act Density 0.000%

    No Known Activations