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

    Neuronpedia

    INDEX
    Explanations

    disasters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     introductory
    -0.07
    bre
    -0.06
    ете
    -0.06
    ounded
    -0.06
    定的
    -0.06
     Judiciary
    -0.06
     Liberals
    -0.06
     multiplication
    -0.06
    nob
    -0.06
    ailles
    -0.06
    POSITIVE LOGITS
    .ease
    0.07
     overturned
    0.07
     effic
    0.07
    ุตสาห
    0.06
    任
    0.06
     �
    0.06
     �
    0.06
    ################################################################
    0.06
     �
    0.06
    .token
    0.06
    Act Density 0.044%

    No Known Activations