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

    Neuronpedia

    INDEX
    Explanations

    base

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marc
    -0.07
     casc
    -0.06
    Æ
    -0.06
    .addComponent
    -0.06
    Degrees
    -0.06
    -click
    -0.06
     edilir
    -0.06
    UCCEEDED
    -0.06
    .slot
    -0.06
     bindings
    -0.06
    POSITIVE LOGITS
     base
    0.07
    .Buffer
    0.06
     itemView
    0.06
    нес
    0.06
    Delta
    0.05
    [action
    0.05
     contentious
    0.05
     healthy
    0.05
     mad
    0.05
     teens
    0.05
    Act Density 0.000%

    No Known Activations