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

    Neuronpedia

    INDEX
    Explanations

    brother and brothers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mr
    0.44
    অ
    0.40
    0.40
     rinnov
    0.39
    forget
    0.38
    Mr
    0.38
     Văn
    0.38
    ही
    0.37
    어서
    0.37
     Sisters
    0.37
    POSITIVE LOGITS
    eniem
    0.42
    畛
    0.40
    效
    0.40
    紂
    0.40
    zeniem
    0.38
    ixels
    0.36
    惪
    0.36
    ulph
    0.36
    jis
    0.35
    ুতে
    0.35
    Act Density 0.003%

    No Known Activations