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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pompeo
    -0.08
     Conf
    -0.07
    累
    -0.07
    istol
    -0.07
     concaten
    -0.07
    ibili
    -0.07
     İn
    -0.07
    踶
    -0.06
    awai
    -0.06
     Din
    -0.06
    POSITIVE LOGITS
    ?<
    0.08
    后
    0.07
    бег
    0.07
    ![
    0.07
     getter
    0.07
    Scheduler
    0.07
    .'/
    0.07
    andidates
    0.07
    \\\\
    0.07
     marginalized
    0.07
    Act Density 0.001%

    No Known Activations