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

    Neuronpedia

    INDEX
    Explanations

    ip addresses and network configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arrhythmia
    0.40
     esperan
    0.40
     umiejęt
    0.39
     diffusivity
    0.38
    ॉन्स
    0.38
     اولم
    0.38
     tillage
    0.38
    MktCap
    0.37
     datth
    0.37
    വന
    0.37
    POSITIVE LOGITS
     localhost
    0.55
    localhost
    0.53
    1
    0.53
    0
    0.47
    gateway
    0.47
     xxx
    0.46
    local
    0.46
    xxx
    0.45
    subnet
    0.43
    x
    0.43
    Act Density 0.021%

    No Known Activations