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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hurt
    -0.07
    ots
    -0.07
    ンフ
    -0.06
    _indexes
    -0.06
     Neville
    -0.06
    �
    -0.06
    ちゃん
    -0.06
    postgres
    -0.06
    害
    -0.06
    dec
    -0.06
    POSITIVE LOGITS
    Journal
    0.07
     Source
    0.07
     PHOTO
    0.07
     eligible
    0.07
     Typical
    0.06
     indicating
    0.06
    AMPLE
    0.06
     enlisted
    0.06
     �
    0.06
    .prepend
    0.06
    Act Density 0.000%

    No Known Activations