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

    Neuronpedia

    INDEX
    Explanations

    ode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (guess
    -0.07
     Рос
    -0.06
     saint
    -0.06
     bullets
    -0.06
     attachments
    -0.06
     foresee
    -0.06
     derivative
    -0.06
     "-"
    -0.06
     credential
    -0.06
     YEAR
    -0.06
    POSITIVE LOGITS
    od
    0.08
    ode
    0.07
    "],
    0.07
    .labels
    0.07
    ODE
    0.07
     Kub
    0.07
    bedo
    0.07
     inode
    0.07
    ilogy
    0.06
    _actor
    0.06
    Act Density 0.002%

    No Known Activations