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

    Neuronpedia

    INDEX
    Explanations

    Roads and trails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    discount
    -0.06
    with
    -0.06
    Credential
    -0.06
     па
    -0.06
    partment
    -0.06
     DETAILS
    -0.06
    seq
    -0.05
     双线
    -0.05
     randomness
    -0.05
    DFS
    -0.05
    POSITIVE LOGITS
     Yorkshire
    0.07
     wirk
    0.07
     continual
    0.06
     PARA
    0.06
     зустрі
    0.06
    .pet
    0.06
     Freddy
    0.06
    ，再
    0.06
    ropsych
    0.06
     enjo
    0.06
    Act Density 0.015%

    No Known Activations