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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pojištění
    -0.06
    بح
    -0.06
    伴
    -0.06
    اهش
    -0.06
    님의
    -0.06
     zemí
    -0.06
    จร
    -0.06
     exporting
    -0.06
    iode
    -0.06
     assessing
    -0.06
    POSITIVE LOGITS
     CSL
    0.07
     घर
    0.07
     Austral
    0.07
     surprisingly
    0.06
    .deck
    0.06
     O
    0.06
     sofas
    0.06
    meler
    0.06
    .solution
    0.06
     assume
    0.06
    Act Density 0.021%

    No Known Activations