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

    Neuronpedia

    INDEX
    Explanations

    names and ratios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     বৈ
    -0.09
    ritur
    -0.08
     contribution
    -0.08
    "But
    -0.07
    Dash
    -0.07
    Pipe
    -0.07
    Also
    -0.07
    lı
    -0.07
     drill
    -0.07
     হিসাবে
    -0.07
    POSITIVE LOGITS
     révé
    0.08
     minutes
    0.07
    ombe
    0.07
     angr
    0.07
     shareholder
    0.07
    ೇ
    0.07
     Sparta
    0.07
     المشتر
    0.07
    ער
    0.07
     вести
    0.07
    Act Density 0.001%

    No Known Activations