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

    Neuronpedia

    INDEX
    Explanations

    mountainous terrain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Su
    0.43
     Su
    0.40
    允
    0.36
    Standard
    0.36
     완성
    0.36
    Congressional
    0.35
     Museum
    0.35
    Common
    0.35
     Standard
    0.35
    FEDERAL
    0.35
    POSITIVE LOGITS
    仞
    0.42
    嫁
    0.42
     പറ
    0.39
    лы
    0.39
     좋을
    0.38
    regs
    0.38
    Terrain
    0.38
    jetas
    0.38
     Terrain
    0.38
    ទេ។
    0.38
    Act Density 0.000%

    No Known Activations