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

    Neuronpedia

    INDEX
    Explanations

    code identifiers and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     craft
    0.43
     glass
    0.42
     manic
    0.41
     ballistic
    0.40
     canvas
    0.40
     accolades
    0.40
     cái
    0.40
     crafts
    0.40
     bubble
    0.39
    爱你
    0.39
    POSITIVE LOGITS
    Nature
    0.43
    social
    0.42
     შორის
    0.41
     Nature
    0.41
    wyczaj
    0.41
     அவர்க
    0.39
     Parte
    0.39
    ándole
    0.39
    <unused226>
    0.39
     зазна
    0.38
    Act Density 0.004%

    No Known Activations