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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     farmhouse
    -0.07
     Rut
    -0.07
     sequential
    -0.07
     Ren
    -0.07
     PUSH
    -0.07
     frogs
    -0.06
    位置
    -0.06
    ศร
    -0.06
    ip
    -0.06
    istence
    -0.06
    POSITIVE LOGITS
     Length
    0.07
    DTD
    0.06
    <!
    0.06
    724
    0.06
    -java
    0.06
     dishonest
    0.06
    αιδ
    0.06
     dear
    0.06
    нимает
    0.06
     getCurrent
    0.06
    Act Density 0.009%

    No Known Activations