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

    Neuronpedia

    INDEX
    Explanations

    medications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hit
    -0.07
     virtually
    -0.07
     Δε
    -0.06
     riff
    -0.06
     않은
    -0.06
    الي
    -0.06
    �
    -0.06
    Payload
    -0.06
    .nlm
    -0.06
     실제
    -0.06
    POSITIVE LOGITS
     reactionary
    0.06
     PASS
    0.06
    Contin
    0.06
     rahatsız
    0.06
     FPGA
    0.06
    _toggle
    0.06
     Vacation
    0.06
     messed
    0.06
    没
    0.06
     inspir
    0.06
    Act Density 0.026%

    No Known Activations