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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical characteristics and conditions of materials and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    physical states and forces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.79
    <unused3>
    -0.67
    <unused14>
    -0.66
    <unused8>
    -0.66
    <unused79>
    -0.66
    <unused43>
    -0.66
    <unused68>
    -0.66
    <unused52>
    -0.66
    <unused28>
    -0.66
    <unused41>
    -0.66
    POSITIVE LOGITS
    évaluateur
    0.37
     Pe
    0.29
    关
    0.29
     She
    0.28
    开
    0.26
     Bre
    0.26
    GridColumn
    0.25
    Pe
    0.25
     pe
    0.25
     counter
    0.24
    Act Density 0.056%

    No Known Activations