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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    중
    -0.06
    _ACT
    -0.06
     Bench
    -0.06
    ��
    -0.06
     floors
    -0.06
     जम
    -0.06
     knives
    -0.05
     Police
    -0.05
    DataSource
    -0.05
     Công
    -0.05
    POSITIVE LOGITS
     Doing
    0.07
    _mar
    0.07
    (($
    0.07
    822
    0.07
    	NdrFc
    0.07
     Spiritual
    0.06
    _Pro
    0.06
    ►
    0.06
    ('').
    0.06
     buluş
    0.06
    Act Density 0.043%

    No Known Activations