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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anky
    -0.08
    .b
    -0.07
    Single
    -0.07
     believe
    -0.07
     single
    -0.07
     positivity
    -0.07
     самостоятель
    -0.07
    Pick
    -0.07
    .microsoft
    -0.07
    ERS
    -0.07
    POSITIVE LOGITS
     בער
    0.09
     стены
    0.09
    씩
    0.09
     paredes
    0.09
    壁
    0.09
     fuma
    0.09
     Regionen
    0.09
    日に
    0.08
     bawat
    0.08
     באזור
    0.08
    Act Density 0.025%

    No Known Activations