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

    Neuronpedia

    INDEX
    Explanations

    high energy and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hardships
    -0.96
     gydy
    -0.96
     sized
    -0.89
    nofollow
    -0.88
    μένων
    -0.88
    ėj
    -0.88
     hoeveel
    -0.88
    اهد
    -0.88
    ことがあります
    -0.86
     inférieure
    -0.85
    POSITIVE LOGITS
     (>
    1.63
    high
    1.30
     high
    1.27
     高
    1.23
    (>
    1.18
    High
    1.09
     उच्च
    1.07
     High
    0.99
     HIGH
    0.97
    dff
    0.91
    Act Density 0.140%

    No Known Activations