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

    Neuronpedia

    INDEX
    Explanations

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Winston
    -0.07
    ォ
    -0.07
     slopes
    -0.06
    bruary
    -0.06
     Prop
    -0.06
    straints
    -0.06
     исполн
    -0.06
     ctype
    -0.06
    .Context
    -0.06
    jav
    -0.06
    POSITIVE LOGITS
    (**
    0.06
    당
    0.06
    Dé
    0.06
    ες
    0.06
     ale
    0.06
     okam
    0.06
    ↑
    0.06
     grotes
    0.06
    izzare
    0.06
    させ
    0.06
    Act Density 0.025%

    No Known Activations