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
    TYPE
    -0.07
     MATERIAL
    -0.07
     debe
    -0.06
    intage
    -0.06
     Attacks
    -0.06
    (RE
    -0.06
     concerted
    -0.06
     bomber
    -0.06
    ebin
    -0.06
     landmark
    -0.06
    POSITIVE LOGITS
     incarcer
    0.07
    came
    0.07
    .distance
    0.07
     �
    0.06
    esinin
    0.06
    816
    0.06
    Він
    0.06
     banker
    0.06
    暂
    0.06
    /back
    0.06
    Act Density 0.001%

    No Known Activations