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

    Neuronpedia

    INDEX
    Explanations

    code documentation/pull requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Styles
    -0.07
     Presence
    -0.06
    」的
    -0.06
     Orb
    -0.06
    anging
    -0.06
     공격
    -0.06
    _eng
    -0.06
     руч
    -0.06
    Mp
    -0.06
    <l
    -0.06
    POSITIVE LOGITS
     gravid
    0.06
     Kant
    0.06
     JOptionPane
    0.06
    [date
    0.06
     slump
    0.06
     limbs
    0.06
    Sy
    0.05
     chickens
    0.05
    iplina
    0.05
     hypoth
    0.05
    Act Density 0.008%

    No Known Activations