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
     setTitle
    -0.08
     moto
    -0.07
    זו
    -0.07
     UIStoryboardSegue
    -0.07
     nie
    -0.07
    NV
    -0.07
    jące
    -0.07
     SEG
    -0.07
    ש
    -0.07
    NH
    -0.07
    POSITIVE LOGITS
    dam
    0.08
    ollapsed
    0.07
                  ↵
    0.07
    预留
    0.07
    цов
    0.07
    pagen
    0.07
     المال
    0.07
    מעמד
    0.06
    _API
    0.06
    замен
    0.06
    Act Density 0.011%

    No Known Activations