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

    Neuronpedia

    INDEX
    Explanations

    phone calls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    handler
    -0.08
    Handler
    -0.08
     handler
    -0.07
     Inspection
    -0.07
    );\
    -0.07
     Manual
    -0.07
    wt
    -0.07
    Relevant
    -0.07
    .Visible
    -0.07
     or
    -0.07
    POSITIVE LOGITS
     ಬರುತ್ತ
    0.10
     आते
    0.09
     apie
    0.09
     வந்து
    0.09
     hampir
    0.08
     এসে
    0.08
    ��
    0.08
     আসে
    0.08
     tentang
    0.08
     килә
    0.08
    Act Density 0.012%

    No Known Activations