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

    Neuronpedia

    INDEX
    Explanations

    vehicles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gae
    -0.07
     ltd
    -0.07
     lotion
    -0.06
    _SUFFIX
    -0.06
    _cmds
    -0.06
    \Application
    -0.06
     decom
    -0.06
     especific
    -0.06
     nắm
    -0.06
    _wrong
    -0.06
    POSITIVE LOGITS
     prompt
    0.06
     prompts
    0.06
    Rib
    0.06
     Depart
    0.06
     teased
    0.06
    	NS
    0.06
    ANGER
    0.06
     sn
    0.06
    Showing
    0.06
     Вар
    0.06
    Act Density 0.035%

    No Known Activations