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

    Neuronpedia

    INDEX
    Explanations

    improved interior, carefully cultivated, depends on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gard
    0.50
     guards
    0.48
    㻁
    0.47
     adjourned
    0.47
    ADDING
    0.46
     opcoes
    0.44
     disturbs
    0.44
     surrendered
    0.44
     protects
    0.43
     gard
    0.43
    POSITIVE LOGITS
     Mode
    0.48
     Organ
    0.47
     NYC
    0.46
     Où
    0.46
     Notably
    0.46
    strate
    0.46
     Correspondence
    0.45
     Πα
    0.44
    map
    0.44
    opoulos
    0.44
    Act Density 0.001%

    No Known Activations