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

    Neuronpedia

    INDEX
    Explanations

    collaboration and collaborative work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ってしまう
    0.38
    ாரி
    0.37
     தொடர்ப
    0.36
     존재
    0.35
     సు
    0.35
     துணை
    0.35
     간
    0.34
    ethylsulfanyl
    0.34
     माइट
    0.34
    厳
    0.34
    POSITIVE LOGITS
     collaborative
    0.70
     collaborate
    0.67
     colabor
    0.66
     colaboración
    0.64
     collaboration
    0.64
     collab
    0.64
    合作
    0.63
     collaborazione
    0.63
     colaborar
    0.61
     Collaborate
    0.60
    Act Density 0.026%

    No Known Activations