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

    Neuronpedia

    INDEX
    Explanations

    escape the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    பட்ச
    0.38
     स्टाफ
    0.37
    يں
    0.36
     Dabei
    0.36
    経営
    0.36
     lavage
    0.36
     بیم
    0.35
    マータイヤ
    0.35
     Estou
    0.35
    ாமல்
    0.35
    POSITIVE LOGITS
    escape
    0.75
     escapes
    0.72
     escape
    0.71
    escap
    0.64
     Escape
    0.62
    goat
    0.59
    Escape
    0.58
     escaped
    0.55
     escapar
    0.52
     hatch
    0.51
    Act Density 0.003%

    No Known Activations