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

    Neuronpedia

    INDEX
    Explanations

    evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xes
    -0.07
     Thomson
    -0.07
     Ranch
    -0.07
    165
    -0.06
    ści
    -0.06
    .session
    -0.06
     top
    -0.06
     locality
    -0.06
    INK
    -0.06
     sin
    -0.06
    POSITIVE LOGITS
     evaluate
    0.09
     evaluated
    0.08
     MVP
    0.08
     Evaluate
    0.07
     EU
    0.07
     evaluating
    0.07
     evaluation
    0.07
    _eval
    0.07
     Auditor
    0.07
     tearDown
    0.07
    Act Density 0.029%

    No Known Activations