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

    Neuronpedia

    INDEX
    Explanations

    future generations face externalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shower
    0.48
     is
    0.46
     role
    0.45
     finger
    0.45
     hydrological
    0.45
     hoard
    0.45
     start
    0.44
     Role
    0.44
     occasionally
    0.43
     The
    0.42
    POSITIVE LOGITS
     substituir
    0.50
    кого
    0.49
    ativ
    0.46
     তৎ
    0.45
     utilizamos
    0.45
     anvä
    0.44
     ಪೂರ್ವ
    0.44
     inapplicable
    0.44
    viol
    0.43
     हमने
    0.43
    Act Density 0.005%

    No Known Activations