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

    Neuronpedia

    INDEX
    Explanations

    Quantum physics/photon detectors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flores
    -0.07
     politics
    -0.07
    algorithm
    -0.07
     Reporting
    -0.07
     hidden
    -0.06
     designers
    -0.06
    _NONE
    -0.06
     parchment
    -0.06
     dirty
    -0.06
     Å
    -0.06
    POSITIVE LOGITS
    poz
    0.07
    "=>"
    0.06
    (cert
    0.06
    Unmount
    0.06
     Ng
    0.06
    (enable
    0.06
     능
    0.06
     sne
    0.06
    rcode
    0.06
    ,t
    0.06
    Act Density 0.020%

    No Known Activations