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

    Neuronpedia

    INDEX
    Explanations

    proposals or methods stated in a research context

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

    propose a method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     /^\
    -0.45
     queſta
    -0.44
     subtotal
    -0.42
     contaminants
    -0.42
     PSI
    -0.42
    trips
    -0.42
    getManager
    -0.41
     contamin
    -0.41
    heatmap
    -0.41
     gonzález
    -0.41
    POSITIVE LOGITS
    Personendaten
    0.69
     proposed
    0.60
    fjspx
    0.54
    CreateModel
    0.53
    LookAnd
    0.53
     invented
    0.52
    VersionUID
    0.52
     suggested
    0.51
     propose
    0.50
     proposing
    0.50
    Act Density 0.029%

    No Known Activations