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

    Neuronpedia

    INDEX
    Explanations

    product/service names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    вал
    -0.07
    えば
    -0.06
    plication
    -0.06
    ắ
    -0.06
     combin
    -0.06
    {}'.
    -0.06
    _filters
    -0.06
     familiarity
    -0.06
     recoil
    -0.06
     її
    -0.06
    POSITIVE LOGITS
     crowned
    0.07
    .VarChar
    0.07
     ภ
    0.07
    *num
    0.07
     Techn
    0.06
     bordered
    0.06
    orrh
    0.06
     bevor
    0.06
    (rot
    0.06
     kond
    0.06
    Act Density 0.150%

    No Known Activations