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

    Neuronpedia

    INDEX
    Explanations

    java

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wap
    -0.08
     louis
    -0.07
    lash
    -0.07
    /new
    -0.06
    ointments
    -0.06
    /code
    -0.06
    且
    -0.06
    legates
    -0.06
    -is
    -0.06
     Complaint
    -0.06
    POSITIVE LOGITS
    braco
    0.07
    ]-
    0.07
    (true
    0.07
    Invocation
    0.06
     stepped
    0.06
    無
    0.06
     навч
    0.06
     alone
    0.06
    実
    0.06
     terr
    0.06
    Act Density 0.006%

    No Known Activations