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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erc
    -0.07
    itals
    -0.07
     норм
    -0.07
    ennes
    -0.06
     ẩm
    -0.06
     asker
    -0.06
     harassment
    -0.06
    Thunk
    -0.06
     dao
    -0.06
    ンフ
    -0.06
    POSITIVE LOGITS
    113
    0.06
    	volatile
    0.06
    	remove
    0.06
    102
    0.06
    112
    0.06
    ılığıyla
    0.06
     falsely
    0.06
    libraries
    0.06
     Software
    0.06
    -mask
    0.06
    Act Density 0.000%

    No Known Activations