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
    unnable
    -0.07
    XXXXXXXX
    -0.07
    oo
    -0.07
    loo
    -0.06
     economies
    -0.06
    os
    -0.06
    Ol
    -0.06
     spot
    -0.06
     [{
    -0.06
    すると
    -0.06
    POSITIVE LOGITS
    (↵
    0.09
    unbind
    0.07
    ((↵
    0.07
     γυνα
    0.07
     sangat
    0.07
    >(↵
    0.07
    rib
    0.07
    ибли
    0.07
     расп
    0.06
    =(↵
    0.06
    Act Density 0.009%

    No Known Activations