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

    Neuronpedia

    INDEX
    Explanations

    wilderness and its contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    1.32
    t
    0.98
    et
    0.97
    ii
    0.91
    st
    0.89
    ij
    0.86
    h
    0.86
    tn
    0.77
    นะ
    0.74
    ng
    0.72
    POSITIVE LOGITS
     wilderness
    0.96
     Wilderness
    0.93
    wilderness
    0.89
    是
    0.84
    филь
    0.82
    فين
    0.77
    愘
    0.77
    ບໍ່
    0.75
     is
    0.72
    ۔
    0.71
    Act Density 0.001%

    No Known Activations