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

    Neuronpedia

    INDEX
    Explanations

    music

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tree
    -0.07
     Python
    -0.07
     noisy
    -0.06
     carefully
    -0.06
     Jennings
    -0.06
     Have
    -0.06
    aro
    -0.06
    -0.06
     Give
    -0.06
     fraud
    -0.06
    POSITIVE LOGITS
     Islamist
    0.06
    lerinde
    0.06
     bahis
    0.06
    ;:;:;:;:
    0.06
    ucs
    0.06
    idores
    0.06
    _completion
    0.06
     ain
    0.06
    resas
    0.06
     yapmaya
    0.06
    Act Density 0.009%

    No Known Activations