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

    Neuronpedia

    INDEX
    Explanations

    rear or back location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     navegador
    0.83
     lubric
    0.79
     canalicul
    0.78
     gwiaz
    0.77
     canola
    0.77
     bathrobe
    0.77
     conval
    0.76
     varietà
    0.76
    ✱
    0.76
     jūs
    0.75
    POSITIVE LOGITS
    s
    1.16
    at
    1.06
    ra
    1.01
    ur
    0.89
    e
    0.84
    ured
    0.84
    el
    0.83
    solving
    0.82
    Backend
    0.81
    sound
    0.80
    Act Density 0.029%

    No Known Activations