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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    task
    -0.07
     festive
    -0.06
    ussels
    -0.06
    |.
    -0.06
    .JWT
    -0.06
     Yunan
    -0.06
    (length
    -0.06
     orch
    -0.06
     joining
    -0.06
     hear
    -0.06
    POSITIVE LOGITS
     invokes
    0.07
     didFinish
    0.06
    SEP
    0.06
    /root
    0.06
    áci
    0.06
    derive
    0.06
     erro
    0.06
    (runtime
    0.06
    .getApp
    0.06
     Wolfe
    0.06
    Act Density 0.020%

    No Known Activations