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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MOV
    -0.08
     convin
    -0.07
    enqueue
    -0.07
    عود
    -0.06
     HAND
    -0.06
    戲
    -0.06
    ”),
    -0.06
    ipelines
    -0.06
     luôn
    -0.06
     Decoration
    -0.06
    POSITIVE LOGITS
    ilebilir
    0.06
     proti
    0.06
    Probability
    0.06
     initiatives
    0.06
    ROKE
    0.06
     Susan
    0.06
    onsense
    0.06
     disproportion
    0.06
    REFERENCE
    0.06
    -terminal
    0.06
    Act Density 0.067%

    No Known Activations