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

    Neuronpedia

    INDEX
    Explanations

    lim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     היחיד
    -0.08
    阿森纳
    -0.07
     Usuario
    -0.07
    ��
    -0.07
     cozy
    -0.07
    ached
    -0.07
    	icon
    -0.07
     credit
    -0.07
     sanitized
    -0.06
    個人
    -0.06
    POSITIVE LOGITS
    entials
    0.08
     underside
    0.07
    畴
    0.07
     paw
    0.07
     Paw
    0.07
    wil
    0.07
    ᵁ
    0.07
    klass
    0.07
     NgModule
    0.07
     Yellow
    0.07
    Act Density 0.004%

    No Known Activations