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

    Neuronpedia

    INDEX
    Explanations

    balance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     മുഴുവ
    0.38
     FullHD
    0.38
     totalitarian
    0.38
     خاصيه
    0.38
    แค
    0.38
    electro
    0.37
    hence
    0.37
    ளிக்க
    0.36
    <0xB1>
    0.36
    kach
    0.36
    POSITIVE LOGITS
     balance
    0.53
    Balance
    0.49
    balance
    0.49
     Balance
    0.47
     BALANCE
    0.46
    balances
    0.44
     balances
    0.42
    バランス
    0.42
    Balances
    0.41
     balancing
    0.40
    Act Density 0.001%

    No Known Activations