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
     данных
    -0.08
     الذه
    -0.07
    ried
    -0.06
    程
    -0.06
    ैं
    -0.06
    ream
    -0.06
     +'
    -0.06
    _),
    -0.06
    firebase
    -0.06
     různé
    -0.06
    POSITIVE LOGITS
     Rodgers
    0.06
     без
    0.06
     issuing
    0.06
     Estr
    0.06
     blanks
    0.06
     coeffs
    0.06
     allev
    0.06
     infused
    0.06
     stockings
    0.06
     placing
    0.06
    Act Density 0.006%

    No Known Activations