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

    Neuronpedia

    INDEX
    Explanations

    -->

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ست
    -0.06
     треба
    -0.06
    Estimated
    -0.06
     фунда
    -0.06
     ml
    -0.06
    _DUMP
    -0.05
     سی
    -0.05
    	Text
    -0.05
    стит
    -0.05
    Delete
    -0.05
    POSITIVE LOGITS
     attaching
    0.07
    calculator
    0.06
     eve
    0.06
    yk
    0.06
    )frame
    0.06
     neat
    0.06
    Κ
    0.06
    Poss
    0.06
    pector
    0.06
    jax
    0.06
    Act Density 0.001%

    No Known Activations