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

    Neuronpedia

    INDEX
    Explanations

    itors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /head
    -0.08
     opcode
    -0.07
    ptic
    -0.07
     Mouse
    -0.07
    Forge
    -0.07
     mash
    -0.06
    licht
    -0.06
     Enlightenment
    -0.06
     weights
    -0.06
    028
    -0.06
    POSITIVE LOGITS
     στις
    0.06
    Fl
    0.06
    Hallo
    0.06
    似
    0.06
     VStack
    0.06
    Binding
    0.06
    .norm
    0.06
     "!
    0.06
    !important
    0.06
    .Accessible
    0.06
    Act Density 0.229%

    No Known Activations