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

    Neuronpedia

    INDEX
    Explanations

    PDF files and online tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trust
    0.40
    镍
    0.38
    五十
    0.38
     சிகிச்ச
    0.37
     Glowing
    0.37
    东南
    0.37
     চেষ্ট
    0.36
    Peach
    0.36
     Trust
    0.36
     Ecosystem
    0.36
    POSITIVE LOGITS
    шком
    0.43
     bell
    0.40
    Celebrate
    0.39
     annoy
    0.38
    Merging
    0.38
     dau
    0.38
     JI
    0.38
     celebrar
    0.37
    simplify
    0.37
    reten
    0.36
    Act Density 0.000%

    No Known Activations