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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sticks
    -0.07
     ended
    -0.07
     Yah
    -0.06
    ...)
    -0.06
    eth
    -0.06
    bcrypt
    -0.06
    따
    -0.06
    ISP
    -0.06
     นาง
    -0.06
     sparked
    -0.06
    POSITIVE LOGITS
    見
    0.07
     domest
    0.07
     dealloc
    0.06
     shame
    0.06
    Mutation
    0.06
    ambia
    0.06
    trim
    0.06
    .setString
    0.06
    .dd
    0.06
    aptured
    0.06
    Act Density 0.000%

    No Known Activations