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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ось
    -0.07
    .INPUT
    -0.07
     çevres
    -0.06
     hence
    -0.06
    ी-
    -0.06
     comfy
    -0.06
     cupboard
    -0.06
    >;
    -0.06
    .details
    -0.06
     khô
    -0.06
    POSITIVE LOGITS
    계획
    0.06
     Mast
    0.06
    ела
    0.06
     earned
    0.06
     Denied
    0.06
    tes
    0.06
    iatrics
    0.06
     Bridge
    0.06
    713
    0.06
     lst
    0.06
    Act Density 0.000%

    No Known Activations