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

    Neuronpedia

    INDEX
    Explanations

    Norwegian mammals and space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    మయ్య
    0.41
    荷重
    0.38
    Mapper
    0.38
    収納
    0.37
    entertain
    0.36
     Load
    0.36
     ভর্ত
    0.36
    စီး
    0.36
     عین
    0.36
     แต่
    0.35
    POSITIVE LOGITS
    舔
    0.46
     ENEM
    0.46
     to
    0.44
     να
    0.43
    𝙸
    0.40
     posl
    0.38
     lepší
    0.37
    Enemy
    0.37
     Patri
    0.36
    best
    0.36
    Act Density 0.001%

    No Known Activations