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

    Neuronpedia

    INDEX
    Explanations

    429

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CFR
    -0.07
    gcc
    -0.07
     bras
    -0.06
    kre
    -0.06
    -pills
    -0.06
    Grammar
    -0.06
     awful
    -0.06
    оров
    -0.06
     süre
    -0.06
     glut
    -0.06
    POSITIVE LOGITS
     depressing
    0.07
     stage
    0.07
    iliated
    0.07
    τές
    0.07
     Materials
    0.06
     harvested
    0.06
    Bron
    0.06
     heated
    0.06
    resentation
    0.06
     ObjectMapper
    0.06
    Act Density 0.000%

    No Known Activations