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

    Neuronpedia

    INDEX
    Explanations

    Drake, English, history, environment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Core
    0.48
    HR
    0.47
    ded
    0.46
    pm
    0.45
    hr
    0.45
    ht
    0.45
    ett
    0.45
    det
    0.44
    7
    0.44
    LR
    0.44
    POSITIVE LOGITS
    𝚒
    0.49
     activités
    0.47
     organs
    0.47
     informatique
    0.47
     wanted
    0.46
     amicable
    0.46
     bred
    0.45
     cysts
    0.45
     êtres
    0.45
     assurances
    0.44
    Act Density 0.001%

    No Known Activations