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

    Neuronpedia

    INDEX
    Explanations

    cryo- words and freeze

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ذی
    0.40
    糖尿
    0.38
     murmur
    0.38
     غذا
    0.36
     sciatic
    0.36
    ovna
    0.35
     murmured
    0.35
    电线路
    0.35
    ছি
    0.35
    锌
    0.34
    POSITIVE LOGITS
    istic
    0.38
     Falcon
    0.37
     Later
    0.37
     Al
    0.37
     Protection
    0.36
     IMF
    0.36
     Pen
    0.36
     Jenkins
    0.36
    all
    0.35
     Freeze
    0.35
    Act Density 0.001%

    No Known Activations