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

    Neuronpedia

    INDEX
    Explanations

    key improvements and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     निर
    0.41
    รร
    0.37
    SizeF
    0.36
    सत्ता
    0.36
    簿
    0.35
     Quin
    0.35
    𝒟
    0.35
    ocin
    0.35
    Curt
    0.35
     MRD
    0.35
    POSITIVE LOGITS
     شرح
    0.40
    key
    0.38
    ckenridge
    0.37
    artha
    0.37
    楔
    0.36
     key
    0.35
     поза
    0.35
    క్ష్
    0.35
    缦
    0.34
    rosse
    0.34
    Act Density 0.013%

    No Known Activations