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

    Neuronpedia

    INDEX
    Explanations

    archive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prohib
    -0.07
    続
    -0.07
    users
    -0.07
    136
    -0.06
    Confirmed
    -0.06
    thin
    -0.06
     thrilling
    -0.06
    應
    -0.06
    OF
    -0.06
     ||
    -0.06
    POSITIVE LOGITS
    ERVICE
    0.06
     Camel
    0.06
     torch
    0.06
    src
    0.06
    sav
    0.06
     Tcl
    0.06
    เธอ
    0.06
     "="
    0.06
     науки
    0.06
    "]
    0.06
    Act Density 0.000%

    No Known Activations