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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bla
    -0.07
    からは
    -0.07
     spokeswoman
    -0.06
    messages
    -0.06
    Cha
    -0.06
    .ro
    -0.06
    Php
    -0.06
    _eof
    -0.06
    .phase
    -0.06
    _WINDOWS
    -0.06
    POSITIVE LOGITS
     k
    0.07
     ****************
    0.07
     crafting
    0.07
    EAR
    0.06
     ---↵
    0.06
     Targets
    0.06
    inke
    0.06
     Mare
    0.06
    \n
    0.06
    μία
    0.06
    Act Density 0.001%

    No Known Activations