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

    Neuronpedia

    INDEX
    Explanations

    sure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     car
    -0.07
    licos
    -0.07
     est
    -0.07
    larda
    -0.06
    Diese
    -0.06
    ]},
    -0.06
    Reg
    -0.06
     specify
    -0.06
     is
    -0.06
    	Model
    -0.06
    POSITIVE LOGITS
    contra
    0.07
    aryl
    0.06
    rates
    0.06
    IMITIVE
    0.06
    уст
    0.06
     korum
    0.06
     soutěže
    0.06
     bakeca
    0.06
    иру
    0.06
    CBC
    0.06
    Act Density 0.099%

    No Known Activations