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

    Neuronpedia

    INDEX
    Explanations

    </

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (newUser
    -0.07
     nut
    -0.07
     Blues
    -0.07
    こ
    -0.07
     cont
    -0.06
     Rot
    -0.06
    restore
    -0.06
    [prop
    -0.06
     mut
    -0.06
     Mic
    -0.06
    POSITIVE LOGITS
    GENER
    0.08
    援助
    0.08
    蒋介石
    0.07
     abundance
    0.07
     japan
    0.07
    _An
    0.07
    aub
    0.07
    État
    0.07
    andas
    0.07
    Ë
    0.07
    Act Density 0.001%

    No Known Activations