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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ştir
    -0.08
     windy
    -0.07
     बड
    -0.07
    ंजन
    -0.07
     лов
    -0.07
     Ket
    -0.06
    )}>
    -0.06
    Cadastro
    -0.06
    ‌است
    -0.06
    ])/
    -0.06
    POSITIVE LOGITS
     specialists
    0.07
    *S
    0.06
    akening
    0.06
    ensors
    0.06
     Conditional
    0.06
     Estados
    0.06
     expressed
    0.06
    	Transform
    0.06
    	e
    0.05
    	In
    0.05
    Act Density 0.001%

    No Known Activations