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

    Neuronpedia

    INDEX
    Explanations

    застав

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SpecWarn
    -0.07
     Verfügung
    -0.07
     değildir
    -0.07
     steak
    -0.07
     язы
    -0.06
    inski
    -0.06
    その
    -0.06
    -Semit
    -0.06
     remember
    -0.06
     dư
    -0.06
    POSITIVE LOGITS
     teachings
    0.08
     leave
    0.07
    激
    0.07
    modern
    0.06
     indul
    0.06
     leads
    0.06
    lessness
    0.06
     locking
    0.06
     letting
    0.06
     teaches
    0.06
    Act Density 0.012%

    No Known Activations