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

    Neuronpedia

    INDEX
    Explanations

    running meetings and workshops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sure
    -0.07
    暂
    -0.06
     Certain
    -0.06
     للد
    -0.06
    ------+
    -0.06
     الوص
    -0.06
     delighted
    -0.06
     personally
    -0.06
    Warn
    -0.06
    vides
    -0.06
    POSITIVE LOGITS
     shl
    0.06
    tam
    0.06
     occupation
    0.06
     raj
    0.06
     payroll
    0.06
     ethn
    0.06
     voy
    0.06
     eser
    0.06
     TB
    0.06
     şun
    0.06
    Act Density 0.017%

    No Known Activations