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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hereditary
    -0.07
     contextual
    -0.07
     belakang
    -0.07
     dwar
    -0.07
    izabeth
    -0.07
     Post
    -0.07
    ftar
    -0.07
    输出
    -0.07
     Nom
    -0.07
    .wrapper
    -0.07
    POSITIVE LOGITS
     rewarded
    0.12
     rewarding
    0.11
    removed
    0.11
     remover
    0.10
     reward
    0.10
    Removed
    0.10
     rewards
    0.10
     removal
    0.10
     triggered
    0.10
     remov
    0.10
    Act Density 0.005%

    No Known Activations