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

    Neuronpedia

    INDEX
    Explanations

    Code/technical errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hawk
    -0.07
    雲
    -0.07
     прох
    -0.07
    _meas
    -0.06
    ่วน
    -0.06
     fuck
    -0.06
     mirrors
    -0.06
     crane
    -0.06
     همین
    -0.06
    ped
    -0.06
    POSITIVE LOGITS
    akedirs
    0.06
    	exit
    0.06
     UserProfile
    0.06
     kann
    0.06
    _particles
    0.06
    )>↵
    0.06
    ARCHAR
    0.06
    Developer
    0.06
     ode
    0.06
    ительное
    0.06
    Act Density 0.000%

    No Known Activations