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

    Neuronpedia

    INDEX
    Explanations

    material testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     approves
    -0.06
     clicks
    -0.06
     Schools
    -0.06
    intros
    -0.06
     Bale
    -0.06
    에도
    -0.06
     peaceful
    -0.06
     cela
    -0.06
     irritated
    -0.05
    ausal
    -0.05
    POSITIVE LOGITS
     Dir
    0.07
     Mozilla
    0.07
    友
    0.07
    émon
    0.07
    .sell
    0.07
     ζω
    0.06
     الکتر
    0.06
    _Return
    0.06
     pově
    0.06
    αν
    0.06
    Act Density 0.054%

    No Known Activations