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

    Neuronpedia

    INDEX
    Explanations

    Research findings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tamp
    -0.08
    Unless
    -0.07
     pointless
    -0.07
    Mutable
    -0.07
    berman
    -0.07
     unless
    -0.07
    ongyang
    -0.07
     Meng
    -0.07
     Unless
    -0.07
    184
    -0.07
    POSITIVE LOGITS
    -east
    0.07
     gsl
    0.06
     Res
    0.06
    /met
    0.06
    eted
    0.06
    -East
    0.06
     tcb
    0.06
     glob
    0.06
    isateur
    0.06
     pelo
    0.06
    Act Density 0.094%

    No Known Activations