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

    Neuronpedia

    INDEX
    Explanations

    diverse text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     auroit
    -0.66
    Needs
    -0.66
    needs
    -0.66
    )__
    -0.62
     feroit
    -0.59
     blij
    -0.57
     pouvoit
    -0.57
     étoit
    -0.56
     chaleur
    -0.56
    zwald
    -0.56
    POSITIVE LOGITS
     try
    0.75
     TRY
    0.57
     throw
    0.57
     attempt
    0.56
    tvguidetime
    0.53
    ագրություններ
    0.50
     add
    0.49
     Try
    0.49
     offer
    0.48
    AddTagHelper
    0.47
    Act Density 0.001%

    No Known Activations