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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     -↵↵
    -0.07
    村党支部
    -0.07
    .bp
    -0.07
     till
    -0.07
     Pin
    -0.07
    以前
    -0.06
    ,K
    -0.06
    ibility
    -0.06
     libero
    -0.06
    .lin
    -0.06
    POSITIVE LOGITS
     сит
    0.08
    -inst
    0.08
    出动
    0.08
     хот
    0.08
    砑
    0.08
    (::
    0.08
     Hearts
    0.07
     restarting
    0.07
    	Application
    0.07
    (actions
    0.07
    Act Density 0.000%

    No Known Activations