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

    Neuronpedia

    INDEX
    Explanations

    coding terms related to file handling and access permissions

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

    fileprivate var, #define, related to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -1.08
    GEBURTSDATUM
    -1.02
     Administrativna
    -1.02
    ſſung
    -1.01
     Biôgrafia
    -0.98
    <unused43>
    -0.96
    <unused41>
    -0.95
    <unused74>
    -0.95
    <pad>
    -0.95
    <unused20>
    -0.94
    POSITIVE LOGITS
    filepath
    0.98
    ↵↵
    0.61
    ↵↵↵
    0.52
     filepath
    0.52
    The
    0.50
    ↵↵↵↵
    0.49
    ↵↵↵↵↵↵
    0.49
     the
    0.49
    ↵
    0.48
    <eos>
    0.43
    Act Density 0.000%

    No Known Activations