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

    Neuronpedia

    INDEX
    Explanations

    Living

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mine
    -0.07
    .location
    -0.07
    unsafe
    -0.07
    .collections
    -0.07
     Mine
    -0.07
     forums
    -0.06
     posi
    -0.06
    .plugin
    -0.06
     informat
    -0.06
     mega
    -0.06
    POSITIVE LOGITS
     Treasury
    0.07
    实施
    0.06
    	LL
    0.06
                            
↵
    0.06
    SW
    0.06
    Chooser
    0.06
     Nixon
    0.06
    vell
    0.06
     Politico
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations