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

    Neuronpedia

    INDEX
    Explanations

    beads

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DllImport
    -0.08
    甘
    -0.07
     wanting
    -0.07
    🇲
    -0.07
     \"%
    -0.07
    izzling
    -0.06
     Wyoming
    -0.06
     history
    -0.06
    残酷
    -0.06
    diet
    -0.06
    POSITIVE LOGITS
    ة
    0.08
    strate
    0.07
     Syndrome
    0.07
     civic
    0.07
    𝔢
    0.07
    icast
    0.07
     Opera
    0.07
     szczególnie
    0.07
     Monica
    0.07
    ー�
    0.07
    Act Density 0.001%

    No Known Activations